
import numpy as np
import matplotlib.pyplot as plt
%matplotlib inline
import pandas as pd
import seaborn as sns
import warnings
warnings.filterwarnings("ignore")
import itertools


application_data = pd.read_csv(r'application_data.csv')
previous_application = pd.read_csv(r'previous_application.csv')
columns_description = pd.read_csv(r'columns_description.csv',skiprows=1)


print ("application_data     :",application_data.shape)
print ("previous_application :",previous_application.shape)
print ("columns_description  :",columns_description.shape)

application_data     : (307511, 122)
previous_application : (1670214, 37)
columns_description  : (159, 5)


pd.set_option("display.max_rows", None, "display.max_columns", None)
display("application_data")
display(application_data.head(3))

'application_data'


display("previous_application ")
display(previous_application.head(3))

'previous_application '


display("columns_description")
pd.set_option('display.max_colwidth', -1)
columns_description=columns_description.drop(['1'],axis=1)
display(columns_description)

'columns_description'


fig = plt.figure(figsize=(18,6))
miss_previous_application = pd.DataFrame((previous_application.isnull().sum())*100/previous_application.shape[0]).reset_index()
miss_previous_application["type"] = "previous_application"
ax = sns.pointplot("index",0,data=miss_previous_application,hue="type")
plt.xticks(rotation =90,fontsize =7)
plt.title("Percentage of Missing values in previous_application")
plt.ylabel("PERCENTAGE")
plt.xlabel("COLUMNS")
ax.set_facecolor("k")
fig.set_facecolor("lightgrey")


round(100*(previous_application.isnull().sum()/len(previous_application.index)),2)

SK_ID_PREV                     0.00 
SK_ID_CURR                     0.00 
NAME_CONTRACT_TYPE             0.00 
AMT_ANNUITY                    22.29
AMT_APPLICATION                0.00 
AMT_CREDIT                     0.00 
AMT_DOWN_PAYMENT               53.64
AMT_GOODS_PRICE                23.08
WEEKDAY_APPR_PROCESS_START     0.00 
HOUR_APPR_PROCESS_START        0.00 
FLAG_LAST_APPL_PER_CONTRACT    0.00 
NFLAG_LAST_APPL_IN_DAY         0.00 
RATE_DOWN_PAYMENT              53.64
RATE_INTEREST_PRIMARY          99.64
RATE_INTEREST_PRIVILEGED       99.64
NAME_CASH_LOAN_PURPOSE         0.00 
NAME_CONTRACT_STATUS           0.00 
DAYS_DECISION                  0.00 
NAME_PAYMENT_TYPE              0.00 
CODE_REJECT_REASON             0.00 
NAME_TYPE_SUITE                49.12
NAME_CLIENT_TYPE               0.00 
NAME_GOODS_CATEGORY            0.00 
NAME_PORTFOLIO                 0.00 
NAME_PRODUCT_TYPE              0.00 
CHANNEL_TYPE                   0.00 
SELLERPLACE_AREA               0.00 
NAME_SELLER_INDUSTRY           0.00 
CNT_PAYMENT                    22.29
NAME_YIELD_GROUP               0.00 
PRODUCT_COMBINATION            0.02 
DAYS_FIRST_DRAWING             40.30
DAYS_FIRST_DUE                 40.30
DAYS_LAST_DUE_1ST_VERSION      40.30
DAYS_LAST_DUE                  40.30
DAYS_TERMINATION               40.30
NFLAG_INSURED_ON_APPROVAL      40.30
dtype: float64


previous_application=previous_application.drop([ 'AMT_DOWN_PAYMENT', 'RATE_DOWN_PAYMENT', 'RATE_INTEREST_PRIMARY',
       "RATE_INTEREST_PRIVILEGED"],axis=1)


fig = plt.figure(figsize=(18,6))
miss_previous_application = pd.DataFrame((previous_application.isnull().sum())*100/previous_application.shape[0]).reset_index()
miss_previous_application["type"] = "previous_application"
ax = sns.pointplot("index",0,data=miss_previous_application,hue="type")
plt.xticks(rotation =90,fontsize =7)
plt.title("Percentage of Missing values in previous_application")
plt.ylabel("PERCENTAGE")
plt.xlabel("COLUMNS")
ax.set_facecolor("k")
fig.set_facecolor("lightgrey")


round(100*(previous_application.isnull().sum()/len(previous_application.index)),2)

SK_ID_PREV                     0.00 
SK_ID_CURR                     0.00 
NAME_CONTRACT_TYPE             0.00 
AMT_ANNUITY                    22.29
AMT_APPLICATION                0.00 
AMT_CREDIT                     0.00 
AMT_GOODS_PRICE                23.08
WEEKDAY_APPR_PROCESS_START     0.00 
HOUR_APPR_PROCESS_START        0.00 
FLAG_LAST_APPL_PER_CONTRACT    0.00 
NFLAG_LAST_APPL_IN_DAY         0.00 
NAME_CASH_LOAN_PURPOSE         0.00 
NAME_CONTRACT_STATUS           0.00 
DAYS_DECISION                  0.00 
NAME_PAYMENT_TYPE              0.00 
CODE_REJECT_REASON             0.00 
NAME_TYPE_SUITE                49.12
NAME_CLIENT_TYPE               0.00 
NAME_GOODS_CATEGORY            0.00 
NAME_PORTFOLIO                 0.00 
NAME_PRODUCT_TYPE              0.00 
CHANNEL_TYPE                   0.00 
SELLERPLACE_AREA               0.00 
NAME_SELLER_INDUSTRY           0.00 
CNT_PAYMENT                    22.29
NAME_YIELD_GROUP               0.00 
PRODUCT_COMBINATION            0.02 
DAYS_FIRST_DRAWING             40.30
DAYS_FIRST_DUE                 40.30
DAYS_LAST_DUE_1ST_VERSION      40.30
DAYS_LAST_DUE                  40.30
DAYS_TERMINATION               40.30
NFLAG_INSURED_ON_APPROVAL      40.30
dtype: float64


print("AMT_ANNUITY NULL COUNT:" ,previous_application['AMT_ANNUITY'].isnull().sum())

AMT_ANNUITY NULL COUNT: 372235


previous_application['AMT_ANNUITY'].describe()

count    1.297979e+06
mean     1.595512e+04
std      1.478214e+04
min      0.000000e+00
25%      6.321780e+03
50%      1.125000e+04
75%      2.065842e+04
max      4.180581e+05
Name: AMT_ANNUITY, dtype: float64


sns.set_style('whitegrid') 
sns.distplot(previous_application['AMT_ANNUITY']) 
plt.show()


print("AMT_GOODS_PRICE NULL COUNT:" ,previous_application['AMT_GOODS_PRICE'].isnull().sum())

AMT_GOODS_PRICE NULL COUNT: 385515


previous_application['AMT_GOODS_PRICE'].describe()

count    1.284699e+06
mean     2.278473e+05
std      3.153966e+05
min      0.000000e+00
25%      5.084100e+04
50%      1.123200e+05
75%      2.340000e+05
max      6.905160e+06
Name: AMT_GOODS_PRICE, dtype: float64


sns.set_style('whitegrid') 
sns.distplot(previous_application['AMT_GOODS_PRICE']) 
plt.show()


print("NAME_TYPE_SUITE NULL COUNT:" ,previous_application['NAME_TYPE_SUITE'].isnull().sum())

NAME_TYPE_SUITE NULL COUNT: 820405


previous_application['NAME_TYPE_SUITE'].value_counts()

Unaccompanied      508970
Family             213263
Spouse, partner    67069 
Children           31566 
Other_B            17624 
Other_A            9077  
Group of people    2240  
Name: NAME_TYPE_SUITE, dtype: int64


print("CNT_PAYMENT NULL COUNT:" ,previous_application['CNT_PAYMENT'].isnull().sum())

CNT_PAYMENT NULL COUNT: 372230


previous_application['CNT_PAYMENT'].describe()

count    1.297984e+06
mean     1.605408e+01
std      1.456729e+01
min      0.000000e+00
25%      6.000000e+00
50%      1.200000e+01
75%      2.400000e+01
max      8.400000e+01
Name: CNT_PAYMENT, dtype: float64


sns.set_style('whitegrid') 
sns.boxplot(previous_application['CNT_PAYMENT']) 
plt.show()


print("DAYS_FIRST_DRAWING :" ,previous_application['CNT_PAYMENT'].isnull().sum())

DAYS_FIRST_DRAWING : 372230


previous_application['DAYS_FIRST_DRAWING'].describe()

count    997149.000000
mean     342209.855039
std      88916.115834 
min     -2922.000000  
25%      365243.000000
50%      365243.000000
75%      365243.000000
max      365243.000000
Name: DAYS_FIRST_DRAWING, dtype: float64


sns.set_style('whitegrid') 
sns.boxplot(previous_application['DAYS_FIRST_DRAWING']) 
plt.show()


print("DAYS_FIRST_DUE :" ,previous_application['DAYS_FIRST_DUE'].isnull().sum())

DAYS_FIRST_DUE : 673065


previous_application['DAYS_FIRST_DUE'].describe()

count    997149.000000
mean     13826.269337 
std      72444.869708 
min     -2892.000000  
25%     -1628.000000  
50%     -831.000000   
75%     -411.000000   
max      365243.000000
Name: DAYS_FIRST_DUE, dtype: float64


sns.set_style('whitegrid') 
sns.boxplot(previous_application['DAYS_FIRST_DUE']) 
plt.show()


print("DAYS_LAST_DUE_1ST_VERSION :" ,previous_application['DAYS_LAST_DUE_1ST_VERSION'].isnull().sum())

DAYS_LAST_DUE_1ST_VERSION : 673065


previous_application['DAYS_LAST_DUE_1ST_VERSION'].describe()

count    997149.000000
mean     33767.774054 
std      106857.034789
min     -2801.000000  
25%     -1242.000000  
50%     -361.000000   
75%      129.000000   
max      365243.000000
Name: DAYS_LAST_DUE_1ST_VERSION, dtype: float64


sns.set_style('whitegrid') 
sns.boxplot(previous_application['DAYS_LAST_DUE_1ST_VERSION']) 
plt.show()


print("DAYS_LAST_DUE:" ,previous_application['DAYS_LAST_DUE'].isnull().sum())

DAYS_LAST_DUE: 673065


previous_application['DAYS_LAST_DUE'].describe()

count    997149.000000
mean     76582.403064 
std      149647.415123
min     -2889.000000  
25%     -1314.000000  
50%     -537.000000   
75%     -74.000000    
max      365243.000000
Name: DAYS_LAST_DUE, dtype: float64


sns.set_style('whitegrid') 
sns.boxplot(previous_application['DAYS_LAST_DUE']) 
plt.show()


print("DAYS_TERMINATION :" ,previous_application['DAYS_TERMINATION'].isnull().sum())

DAYS_TERMINATION : 673065


previous_application['DAYS_TERMINATION'].describe()

count    997149.000000
mean     81992.343838 
std      153303.516729
min     -2874.000000  
25%     -1270.000000  
50%     -499.000000   
75%     -44.000000    
max      365243.000000
Name: DAYS_TERMINATION, dtype: float64


sns.set_style('whitegrid') 
sns.boxplot(previous_application['DAYS_TERMINATION']) 
plt.show()


print("NFLAG_INSURED_ON_APPROVAL:" ,previous_application['NFLAG_INSURED_ON_APPROVAL'].isnull().sum())

NFLAG_INSURED_ON_APPROVAL: 673065


previous_application['NFLAG_INSURED_ON_APPROVAL'].value_counts()

0.0    665527
1.0    331622
Name: NFLAG_INSURED_ON_APPROVAL, dtype: int64


previous_application.isnull().sum()

SK_ID_PREV                     0     
SK_ID_CURR                     0     
NAME_CONTRACT_TYPE             0     
AMT_ANNUITY                    372235
AMT_APPLICATION                0     
AMT_CREDIT                     1     
AMT_GOODS_PRICE                385515
WEEKDAY_APPR_PROCESS_START     0     
HOUR_APPR_PROCESS_START        0     
FLAG_LAST_APPL_PER_CONTRACT    0     
NFLAG_LAST_APPL_IN_DAY         0     
NAME_CASH_LOAN_PURPOSE         0     
NAME_CONTRACT_STATUS           0     
DAYS_DECISION                  0     
NAME_PAYMENT_TYPE              0     
CODE_REJECT_REASON             0     
NAME_TYPE_SUITE                820405
NAME_CLIENT_TYPE               0     
NAME_GOODS_CATEGORY            0     
NAME_PORTFOLIO                 0     
NAME_PRODUCT_TYPE              0     
CHANNEL_TYPE                   0     
SELLERPLACE_AREA               0     
NAME_SELLER_INDUSTRY           0     
CNT_PAYMENT                    372230
NAME_YIELD_GROUP               0     
PRODUCT_COMBINATION            346   
DAYS_FIRST_DRAWING             673065
DAYS_FIRST_DUE                 673065
DAYS_LAST_DUE_1ST_VERSION      673065
DAYS_LAST_DUE                  673065
DAYS_TERMINATION               673065
NFLAG_INSURED_ON_APPROVAL      673065
dtype: int64


print("AMT_CREDIT :" ,previous_application['AMT_CREDIT'].isnull().sum())

AMT_CREDIT : 1


previous_application['AMT_CREDIT'].describe()

count    1.670213e+06
mean     1.961140e+05
std      3.185746e+05
min      0.000000e+00
25%      2.416050e+04
50%      8.054100e+04
75%      2.164185e+05
max      6.905160e+06
Name: AMT_CREDIT, dtype: float64


sns.set_style('whitegrid') 
sns.boxplot(previous_application['AMT_CREDIT']) 
plt.show()


print("PRODUCT_COMBINATION :" ,previous_application['PRODUCT_COMBINATION'].isnull().sum())

PRODUCT_COMBINATION : 346


previous_application['PRODUCT_COMBINATION'].value_counts()

Cash                              285990
POS household with interest       263622
POS mobile with interest          220670
Cash X-Sell: middle               143883
Cash X-Sell: low                  130248
Card Street                       112582
POS industry with interest        98833 
POS household without interest    82908 
Card X-Sell                       80582 
Cash Street: high                 59639 
Cash X-Sell: high                 59301 
Cash Street: middle               34658 
Cash Street: low                  33834 
POS mobile without interest       24082 
POS other with interest           23879 
POS industry without interest     12602 
POS others without interest       2555  
Name: PRODUCT_COMBINATION, dtype: int64


class color:
   PURPLE = '\033[95m'
   CYAN = '\033[96m'
   DARKCYAN = '\033[36m'
   BLUE = '\033[94m'
   GREEN = '\033[92m'
   YELLOW = '\033[93m'
   RED = '\033[91m'
   BOLD = '\033[1m'
   UNDERLINE = '\033[4m'
   END = '\033[0m'


obj_dtypes = [i for i in previous_application.select_dtypes(include=object).columns if i not in ["type"] ]
num_dtypes = [i for i in previous_application.select_dtypes(include = np.number).columns if i not in ['SK_ID_CURR'] + [ 'TARGET']]


print(color.BOLD + color.PURPLE + 'Categorical Columns' + color.END, "\n")
for x in range(len(obj_dtypes)): 
    print(obj_dtypes[x])

Categorical Columns 

NAME_CONTRACT_TYPE
WEEKDAY_APPR_PROCESS_START
FLAG_LAST_APPL_PER_CONTRACT
NAME_CASH_LOAN_PURPOSE
NAME_CONTRACT_STATUS
NAME_PAYMENT_TYPE
CODE_REJECT_REASON
NAME_TYPE_SUITE
NAME_CLIENT_TYPE
NAME_GOODS_CATEGORY
NAME_PORTFOLIO
NAME_PRODUCT_TYPE
CHANNEL_TYPE
NAME_SELLER_INDUSTRY
NAME_YIELD_GROUP
PRODUCT_COMBINATION


print(color.BOLD + color.PURPLE + 'Numerical' + color.END, "\n")
for x in range(len(obj_dtypes)): 
    print(obj_dtypes[x])

Numerical 

NAME_CONTRACT_TYPE
WEEKDAY_APPR_PROCESS_START
FLAG_LAST_APPL_PER_CONTRACT
NAME_CASH_LOAN_PURPOSE
NAME_CONTRACT_STATUS
NAME_PAYMENT_TYPE
CODE_REJECT_REASON
NAME_TYPE_SUITE
NAME_CLIENT_TYPE
NAME_GOODS_CATEGORY
NAME_PORTFOLIO
NAME_PRODUCT_TYPE
CHANNEL_TYPE
NAME_SELLER_INDUSTRY
NAME_YIELD_GROUP
PRODUCT_COMBINATION


fig = plt.figure(figsize=(18,6))
miss_application_data = pd.DataFrame((application_data.isnull().sum())*100/application_data.shape[0]).reset_index()
miss_application_data["type"] = "application_data"
ax = sns.pointplot("index",0,data=miss_application_data,hue="type")
plt.xticks(rotation =90,fontsize =7)
plt.title("Percentage of Missing values in application_data")
plt.ylabel("PERCENTAGE")
plt.xlabel("COLUMNS")
ax.set_facecolor("k")
fig.set_facecolor("lightgrey")


round(100*(application_data.isnull().sum()/len(application_data.index)),2)

SK_ID_CURR                      0.00 
TARGET                          0.00 
NAME_CONTRACT_TYPE              0.00 
CODE_GENDER                     0.00 
FLAG_OWN_CAR                    0.00 
FLAG_OWN_REALTY                 0.00 
CNT_CHILDREN                    0.00 
AMT_INCOME_TOTAL                0.00 
AMT_CREDIT                      0.00 
AMT_ANNUITY                     0.00 
AMT_GOODS_PRICE                 0.09 
NAME_TYPE_SUITE                 0.42 
NAME_INCOME_TYPE                0.00 
NAME_EDUCATION_TYPE             0.00 
NAME_FAMILY_STATUS              0.00 
NAME_HOUSING_TYPE               0.00 
REGION_POPULATION_RELATIVE      0.00 
DAYS_BIRTH                      0.00 
DAYS_EMPLOYED                   0.00 
DAYS_REGISTRATION               0.00 
DAYS_ID_PUBLISH                 0.00 
OWN_CAR_AGE                     65.99
FLAG_MOBIL                      0.00 
FLAG_EMP_PHONE                  0.00 
FLAG_WORK_PHONE                 0.00 
FLAG_CONT_MOBILE                0.00 
FLAG_PHONE                      0.00 
FLAG_EMAIL                      0.00 
OCCUPATION_TYPE                 31.35
CNT_FAM_MEMBERS                 0.00 
REGION_RATING_CLIENT            0.00 
REGION_RATING_CLIENT_W_CITY     0.00 
WEEKDAY_APPR_PROCESS_START      0.00 
HOUR_APPR_PROCESS_START         0.00 
REG_REGION_NOT_LIVE_REGION      0.00 
REG_REGION_NOT_WORK_REGION      0.00 
LIVE_REGION_NOT_WORK_REGION     0.00 
REG_CITY_NOT_LIVE_CITY          0.00 
REG_CITY_NOT_WORK_CITY          0.00 
LIVE_CITY_NOT_WORK_CITY         0.00 
ORGANIZATION_TYPE               0.00 
EXT_SOURCE_1                    56.38
EXT_SOURCE_2                    0.21 
EXT_SOURCE_3                    19.83
APARTMENTS_AVG                  50.75
BASEMENTAREA_AVG                58.52
YEARS_BEGINEXPLUATATION_AVG     48.78
YEARS_BUILD_AVG                 66.50
COMMONAREA_AVG                  69.87
ELEVATORS_AVG                   53.30
ENTRANCES_AVG                   50.35
FLOORSMAX_AVG                   49.76
FLOORSMIN_AVG                   67.85
LANDAREA_AVG                    59.38
LIVINGAPARTMENTS_AVG            68.35
LIVINGAREA_AVG                  50.19
NONLIVINGAPARTMENTS_AVG         69.43
NONLIVINGAREA_AVG               55.18
APARTMENTS_MODE                 50.75
BASEMENTAREA_MODE               58.52
YEARS_BEGINEXPLUATATION_MODE    48.78
YEARS_BUILD_MODE                66.50
COMMONAREA_MODE                 69.87
ELEVATORS_MODE                  53.30
ENTRANCES_MODE                  50.35
FLOORSMAX_MODE                  49.76
FLOORSMIN_MODE                  67.85
LANDAREA_MODE                   59.38
LIVINGAPARTMENTS_MODE           68.35
LIVINGAREA_MODE                 50.19
NONLIVINGAPARTMENTS_MODE        69.43
NONLIVINGAREA_MODE              55.18
APARTMENTS_MEDI                 50.75
BASEMENTAREA_MEDI               58.52
YEARS_BEGINEXPLUATATION_MEDI    48.78
YEARS_BUILD_MEDI                66.50
COMMONAREA_MEDI                 69.87
ELEVATORS_MEDI                  53.30
ENTRANCES_MEDI                  50.35
FLOORSMAX_MEDI                  49.76
FLOORSMIN_MEDI                  67.85
LANDAREA_MEDI                   59.38
LIVINGAPARTMENTS_MEDI           68.35
LIVINGAREA_MEDI                 50.19
NONLIVINGAPARTMENTS_MEDI        69.43
NONLIVINGAREA_MEDI              55.18
FONDKAPREMONT_MODE              68.39
HOUSETYPE_MODE                  50.18
TOTALAREA_MODE                  48.27
WALLSMATERIAL_MODE              50.84
EMERGENCYSTATE_MODE             47.40
OBS_30_CNT_SOCIAL_CIRCLE        0.33 
DEF_30_CNT_SOCIAL_CIRCLE        0.33 
OBS_60_CNT_SOCIAL_CIRCLE        0.33 
DEF_60_CNT_SOCIAL_CIRCLE        0.33 
DAYS_LAST_PHONE_CHANGE          0.00 
FLAG_DOCUMENT_2                 0.00 
FLAG_DOCUMENT_3                 0.00 
FLAG_DOCUMENT_4                 0.00 
FLAG_DOCUMENT_5                 0.00 
FLAG_DOCUMENT_6                 0.00 
FLAG_DOCUMENT_7                 0.00 
FLAG_DOCUMENT_8                 0.00 
FLAG_DOCUMENT_9                 0.00 
FLAG_DOCUMENT_10                0.00 
FLAG_DOCUMENT_11                0.00 
FLAG_DOCUMENT_12                0.00 
FLAG_DOCUMENT_13                0.00 
FLAG_DOCUMENT_14                0.00 
FLAG_DOCUMENT_15                0.00 
FLAG_DOCUMENT_16                0.00 
FLAG_DOCUMENT_17                0.00 
FLAG_DOCUMENT_18                0.00 
FLAG_DOCUMENT_19                0.00 
FLAG_DOCUMENT_20                0.00 
FLAG_DOCUMENT_21                0.00 
AMT_REQ_CREDIT_BUREAU_HOUR      13.50
AMT_REQ_CREDIT_BUREAU_DAY       13.50
AMT_REQ_CREDIT_BUREAU_WEEK      13.50
AMT_REQ_CREDIT_BUREAU_MON       13.50
AMT_REQ_CREDIT_BUREAU_QRT       13.50
AMT_REQ_CREDIT_BUREAU_YEAR      13.50
dtype: float64


fig = plt.figure(figsize=(18,6))
miss_application_data = pd.DataFrame((application_data.isnull().sum())*100/application_data.shape[0]).reset_index()
miss_application_data["type"] = "application_data"
ax = sns.pointplot("index",0,data=miss_application_data,hue="type")
plt.xticks(rotation =90,fontsize =7)
plt.title("Percentage of Missing values in application_data")
plt.ylabel("PERCENTAGE")
plt.xlabel("COLUMNS")
ax.set_facecolor("k")
fig.set_facecolor("lightgrey")


round(100*(application_data.isnull().sum()/len(application_data.index)),2)

SK_ID_CURR                     0.00 
TARGET                         0.00 
NAME_CONTRACT_TYPE             0.00 
CODE_GENDER                    0.00 
FLAG_OWN_CAR                   0.00 
FLAG_OWN_REALTY                0.00 
CNT_CHILDREN                   0.00 
AMT_INCOME_TOTAL               0.00 
AMT_CREDIT                     0.00 
AMT_ANNUITY                    0.00 
AMT_GOODS_PRICE                0.09 
NAME_TYPE_SUITE                0.42 
NAME_INCOME_TYPE               0.00 
NAME_EDUCATION_TYPE            0.00 
NAME_FAMILY_STATUS             0.00 
NAME_HOUSING_TYPE              0.00 
REGION_POPULATION_RELATIVE     0.00 
DAYS_BIRTH                     0.00 
DAYS_EMPLOYED                  0.00 
DAYS_REGISTRATION              0.00 
DAYS_ID_PUBLISH                0.00 
FLAG_MOBIL                     0.00 
FLAG_EMP_PHONE                 0.00 
FLAG_WORK_PHONE                0.00 
FLAG_CONT_MOBILE               0.00 
FLAG_PHONE                     0.00 
FLAG_EMAIL                     0.00 
CNT_FAM_MEMBERS                0.00 
REGION_RATING_CLIENT           0.00 
REGION_RATING_CLIENT_W_CITY    0.00 
WEEKDAY_APPR_PROCESS_START     0.00 
HOUR_APPR_PROCESS_START        0.00 
REG_REGION_NOT_LIVE_REGION     0.00 
REG_REGION_NOT_WORK_REGION     0.00 
LIVE_REGION_NOT_WORK_REGION    0.00 
REG_CITY_NOT_LIVE_CITY         0.00 
REG_CITY_NOT_WORK_CITY         0.00 
LIVE_CITY_NOT_WORK_CITY        0.00 
ORGANIZATION_TYPE              0.00 
OBS_30_CNT_SOCIAL_CIRCLE       0.33 
DEF_30_CNT_SOCIAL_CIRCLE       0.33 
OBS_60_CNT_SOCIAL_CIRCLE       0.33 
DEF_60_CNT_SOCIAL_CIRCLE       0.33 
DAYS_LAST_PHONE_CHANGE         0.00 
FLAG_DOCUMENT_2                0.00 
FLAG_DOCUMENT_3                0.00 
FLAG_DOCUMENT_4                0.00 
FLAG_DOCUMENT_5                0.00 
FLAG_DOCUMENT_6                0.00 
FLAG_DOCUMENT_7                0.00 
FLAG_DOCUMENT_8                0.00 
FLAG_DOCUMENT_9                0.00 
FLAG_DOCUMENT_10               0.00 
FLAG_DOCUMENT_11               0.00 
FLAG_DOCUMENT_12               0.00 
FLAG_DOCUMENT_13               0.00 
FLAG_DOCUMENT_14               0.00 
FLAG_DOCUMENT_15               0.00 
FLAG_DOCUMENT_16               0.00 
FLAG_DOCUMENT_17               0.00 
FLAG_DOCUMENT_18               0.00 
FLAG_DOCUMENT_19               0.00 
FLAG_DOCUMENT_20               0.00 
FLAG_DOCUMENT_21               0.00 
AMT_REQ_CREDIT_BUREAU_HOUR     13.50
AMT_REQ_CREDIT_BUREAU_DAY      13.50
AMT_REQ_CREDIT_BUREAU_WEEK     13.50
AMT_REQ_CREDIT_BUREAU_MON      13.50
AMT_REQ_CREDIT_BUREAU_QRT      13.50
AMT_REQ_CREDIT_BUREAU_YEAR     13.50
dtype: float64


print("AMT_REQ_CREDIT_BUREAU_DAY NAN COUNT :" ,application_data['AMT_REQ_CREDIT_BUREAU_DAY'].isnull().sum())

AMT_REQ_CREDIT_BUREAU_DAY NAN COUNT : 41519


application_data['AMT_REQ_CREDIT_BUREAU_DAY'].describe()

count    265992.000000
mean     0.007000     
std      0.110757     
min      0.000000     
25%      0.000000     
50%      0.000000     
75%      0.000000     
max      9.000000     
Name: AMT_REQ_CREDIT_BUREAU_DAY, dtype: float64


print("AMT_REQ_CREDIT_BUREAU_HOUR NAN COUNT :" ,application_data['AMT_REQ_CREDIT_BUREAU_HOUR'].isnull().sum())

AMT_REQ_CREDIT_BUREAU_HOUR NAN COUNT : 41519


application_data['AMT_REQ_CREDIT_BUREAU_HOUR'].describe()

count    265992.000000
mean     0.006402     
std      0.083849     
min      0.000000     
25%      0.000000     
50%      0.000000     
75%      0.000000     
max      4.000000     
Name: AMT_REQ_CREDIT_BUREAU_HOUR, dtype: float64


print("AMT_REQ_CREDIT_BUREAU_MON NAN COUNT :" ,application_data['AMT_REQ_CREDIT_BUREAU_MON'].isnull().sum())

AMT_REQ_CREDIT_BUREAU_MON NAN COUNT : 41519


application_data['AMT_REQ_CREDIT_BUREAU_MON'].describe()

count    265992.000000
mean     0.267395     
std      0.916002     
min      0.000000     
25%      0.000000     
50%      0.000000     
75%      0.000000     
max      27.000000    
Name: AMT_REQ_CREDIT_BUREAU_MON, dtype: float64


print("AMT_REQ_CREDIT_BUREAU_QRT NAN COUNT :" ,application_data['AMT_REQ_CREDIT_BUREAU_QRT'].isnull().sum())

AMT_REQ_CREDIT_BUREAU_QRT NAN COUNT : 41519


print("AMT_REQ_CREDIT_BUREAU_WEEK NAN COUNT :" ,application_data['AMT_REQ_CREDIT_BUREAU_WEEK'].isnull().sum())

AMT_REQ_CREDIT_BUREAU_WEEK NAN COUNT : 41519


application_data['AMT_REQ_CREDIT_BUREAU_WEEK'].describe()

count    265992.000000
mean     0.034362     
std      0.204685     
min      0.000000     
25%      0.000000     
50%      0.000000     
75%      0.000000     
max      8.000000     
Name: AMT_REQ_CREDIT_BUREAU_WEEK, dtype: float64


print("AMT_REQ_CREDIT_BUREAU_YEAR NAN COUNT :" ,application_data['AMT_REQ_CREDIT_BUREAU_YEAR'].isnull().sum())

AMT_REQ_CREDIT_BUREAU_YEAR NAN COUNT : 41519


application_data['AMT_REQ_CREDIT_BUREAU_YEAR'].describe()

count    265992.000000
mean     1.899974     
std      1.869295     
min      0.000000     
25%      0.000000     
50%      1.000000     
75%      3.000000     
max      25.000000    
Name: AMT_REQ_CREDIT_BUREAU_YEAR, dtype: float64


print("DEF_30_CNT_SOCIAL_CIRCLE NAN COUNT :" ,application_data['DEF_30_CNT_SOCIAL_CIRCLE'].isnull().sum())

DEF_30_CNT_SOCIAL_CIRCLE NAN COUNT : 1021


application_data['DEF_30_CNT_SOCIAL_CIRCLE'].describe()

count    306490.000000
mean     0.143421     
std      0.446698     
min      0.000000     
25%      0.000000     
50%      0.000000     
75%      0.000000     
max      34.000000    
Name: DEF_30_CNT_SOCIAL_CIRCLE, dtype: float64


print("DEF_30_CNT_SOCIAL_CIRCLE :" ,application_data['DEF_30_CNT_SOCIAL_CIRCLE'].isnull().sum())

DEF_30_CNT_SOCIAL_CIRCLE : 1021


application_data['DEF_30_CNT_SOCIAL_CIRCLE'].describe()

count    306490.000000
mean     0.143421     
std      0.446698     
min      0.000000     
25%      0.000000     
50%      0.000000     
75%      0.000000     
max      34.000000    
Name: DEF_30_CNT_SOCIAL_CIRCLE, dtype: float64


print("OBS_60_CNT_SOCIAL_CIRCLE :" ,application_data['OBS_60_CNT_SOCIAL_CIRCLE'].isnull().sum())

OBS_60_CNT_SOCIAL_CIRCLE : 1021


application_data['OBS_60_CNT_SOCIAL_CIRCLE'].describe()

count    306490.000000
mean     1.405292     
std      2.379803     
min      0.000000     
25%      0.000000     
50%      0.000000     
75%      2.000000     
max      344.000000   
Name: OBS_60_CNT_SOCIAL_CIRCLE, dtype: float64


print("DEF_60_CNT_SOCIAL_CIRCLE :" ,application_data['DEF_60_CNT_SOCIAL_CIRCLE'].isnull().sum())

DEF_60_CNT_SOCIAL_CIRCLE : 1021


application_data['DEF_60_CNT_SOCIAL_CIRCLE'].describe()

count    306490.000000
mean     0.100049     
std      0.362291     
min      0.000000     
25%      0.000000     
50%      0.000000     
75%      0.000000     
max      24.000000    
Name: DEF_60_CNT_SOCIAL_CIRCLE, dtype: float64


application_data.isnull().sum()

SK_ID_CURR                     0    
TARGET                         0    
NAME_CONTRACT_TYPE             0    
CODE_GENDER                    0    
FLAG_OWN_CAR                   0    
FLAG_OWN_REALTY                0    
CNT_CHILDREN                   0    
AMT_INCOME_TOTAL               0    
AMT_CREDIT                     0    
AMT_ANNUITY                    12   
AMT_GOODS_PRICE                278  
NAME_TYPE_SUITE                1292 
NAME_INCOME_TYPE               0    
NAME_EDUCATION_TYPE            0    
NAME_FAMILY_STATUS             0    
NAME_HOUSING_TYPE              0    
REGION_POPULATION_RELATIVE     0    
DAYS_BIRTH                     0    
DAYS_EMPLOYED                  0    
DAYS_REGISTRATION              0    
DAYS_ID_PUBLISH                0    
FLAG_MOBIL                     0    
FLAG_EMP_PHONE                 0    
FLAG_WORK_PHONE                0    
FLAG_CONT_MOBILE               0    
FLAG_PHONE                     0    
FLAG_EMAIL                     0    
CNT_FAM_MEMBERS                2    
REGION_RATING_CLIENT           0    
REGION_RATING_CLIENT_W_CITY    0    
WEEKDAY_APPR_PROCESS_START     0    
HOUR_APPR_PROCESS_START        0    
REG_REGION_NOT_LIVE_REGION     0    
REG_REGION_NOT_WORK_REGION     0    
LIVE_REGION_NOT_WORK_REGION    0    
REG_CITY_NOT_LIVE_CITY         0    
REG_CITY_NOT_WORK_CITY         0    
LIVE_CITY_NOT_WORK_CITY        0    
ORGANIZATION_TYPE              0    
OBS_30_CNT_SOCIAL_CIRCLE       1021 
DEF_30_CNT_SOCIAL_CIRCLE       1021 
OBS_60_CNT_SOCIAL_CIRCLE       1021 
DEF_60_CNT_SOCIAL_CIRCLE       1021 
DAYS_LAST_PHONE_CHANGE         1    
FLAG_DOCUMENT_2                0    
FLAG_DOCUMENT_3                0    
FLAG_DOCUMENT_4                0    
FLAG_DOCUMENT_5                0    
FLAG_DOCUMENT_6                0    
FLAG_DOCUMENT_7                0    
FLAG_DOCUMENT_8                0    
FLAG_DOCUMENT_9                0    
FLAG_DOCUMENT_10               0    
FLAG_DOCUMENT_11               0    
FLAG_DOCUMENT_12               0    
FLAG_DOCUMENT_13               0    
FLAG_DOCUMENT_14               0    
FLAG_DOCUMENT_15               0    
FLAG_DOCUMENT_16               0    
FLAG_DOCUMENT_17               0    
FLAG_DOCUMENT_18               0    
FLAG_DOCUMENT_19               0    
FLAG_DOCUMENT_20               0    
FLAG_DOCUMENT_21               0    
AMT_REQ_CREDIT_BUREAU_HOUR     41519
AMT_REQ_CREDIT_BUREAU_DAY      41519
AMT_REQ_CREDIT_BUREAU_WEEK     41519
AMT_REQ_CREDIT_BUREAU_MON      41519
AMT_REQ_CREDIT_BUREAU_QRT      41519
AMT_REQ_CREDIT_BUREAU_YEAR     41519
dtype: int64


print("AMT_ANNUITY  :" ,application_data['AMT_ANNUITY'].isnull().sum())

AMT_ANNUITY  : 12


application_data['AMT_ANNUITY'].describe()

count    307499.000000
mean     27108.573909 
std      14493.737315 
min      1615.500000  
25%      16524.000000 
50%      24903.000000 
75%      34596.000000 
max      258025.500000
Name: AMT_ANNUITY, dtype: float64


sns.set_style('whitegrid') 
sns.distplot(application_data['AMT_ANNUITY']) 
plt.show()


print("AMT_GOODS_PRICE   :" ,application_data['AMT_GOODS_PRICE'].isnull().sum())

AMT_GOODS_PRICE   : 278


application_data['AMT_GOODS_PRICE'].describe()

count    3.072330e+05
mean     5.383962e+05
std      3.694465e+05
min      4.050000e+04
25%      2.385000e+05
50%      4.500000e+05
75%      6.795000e+05
max      4.050000e+06
Name: AMT_GOODS_PRICE, dtype: float64


sns.set_style('whitegrid') 
sns.distplot(application_data['AMT_GOODS_PRICE']) 
plt.show()


print("NAME_TYPE_SUITE :" ,application_data['NAME_TYPE_SUITE'].isnull().sum())

NAME_TYPE_SUITE : 1292


application_data['NAME_TYPE_SUITE'].value_counts()

Unaccompanied      248526
Family             40149 
Spouse, partner    11370 
Children           3267  
Other_B            1770  
Other_A            866   
Group of people    271   
Name: NAME_TYPE_SUITE, dtype: int64


print("CNT_FAM_MEMBERS :" ,application_data['CNT_FAM_MEMBERS'].isnull().sum())

CNT_FAM_MEMBERS : 2


application_data['CNT_FAM_MEMBERS'].describe()

count    307509.000000
mean     2.152665     
std      0.910682     
min      1.000000     
25%      2.000000     
50%      2.000000     
75%      3.000000     
max      20.000000    
Name: CNT_FAM_MEMBERS, dtype: float64


sns.set_style('whitegrid') 
sns.distplot(application_data['CNT_FAM_MEMBERS']) 
plt.show()


print("DAYS_LAST_PHONE_CHANGE :" ,application_data['DAYS_LAST_PHONE_CHANGE'].isnull().sum())

DAYS_LAST_PHONE_CHANGE : 1


application_data['DAYS_LAST_PHONE_CHANGE'].describe()

count    307510.000000
mean    -962.858788   
std      826.808487   
min     -4292.000000  
25%     -1570.000000  
50%     -757.000000   
75%     -274.000000   
max      0.000000     
Name: DAYS_LAST_PHONE_CHANGE, dtype: float64


import statistics 
statistics.mode(application_data['DAYS_LAST_PHONE_CHANGE'])

0.0


print(type(application_data.info()))

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 307511 entries, 0 to 307510
Data columns (total 70 columns):
 #   Column                       Non-Null Count   Dtype  
---  ------                       --------------   -----  
 0   SK_ID_CURR                   307511 non-null  int64  
 1   TARGET                       307511 non-null  int64  
 2   NAME_CONTRACT_TYPE           307511 non-null  object 
 3   CODE_GENDER                  307511 non-null  object 
 4   FLAG_OWN_CAR                 307511 non-null  object 
 5   FLAG_OWN_REALTY              307511 non-null  object 
 6   CNT_CHILDREN                 307511 non-null  int64  
 7   AMT_INCOME_TOTAL             307511 non-null  float64
 8   AMT_CREDIT                   307511 non-null  float64
 9   AMT_ANNUITY                  307499 non-null  float64
 10  AMT_GOODS_PRICE              307233 non-null  float64
 11  NAME_TYPE_SUITE              306219 non-null  object 
 12  NAME_INCOME_TYPE             307511 non-null  object 
 13  NAME_EDUCATION_TYPE          307511 non-null  object 
 14  NAME_FAMILY_STATUS           307511 non-null  object 
 15  NAME_HOUSING_TYPE            307511 non-null  object 
 16  REGION_POPULATION_RELATIVE   307511 non-null  float64
 17  DAYS_BIRTH                   307511 non-null  int64  
 18  DAYS_EMPLOYED                307511 non-null  int64  
 19  DAYS_REGISTRATION            307511 non-null  float64
 20  DAYS_ID_PUBLISH              307511 non-null  int64  
 21  FLAG_MOBIL                   307511 non-null  int64  
 22  FLAG_EMP_PHONE               307511 non-null  int64  
 23  FLAG_WORK_PHONE              307511 non-null  int64  
 24  FLAG_CONT_MOBILE             307511 non-null  int64  
 25  FLAG_PHONE                   307511 non-null  int64  
 26  FLAG_EMAIL                   307511 non-null  int64  
 27  CNT_FAM_MEMBERS              307509 non-null  float64
 28  REGION_RATING_CLIENT         307511 non-null  int64  
 29  REGION_RATING_CLIENT_W_CITY  307511 non-null  int64  
 30  WEEKDAY_APPR_PROCESS_START   307511 non-null  object 
 31  HOUR_APPR_PROCESS_START      307511 non-null  int64  
 32  REG_REGION_NOT_LIVE_REGION   307511 non-null  int64  
 33  REG_REGION_NOT_WORK_REGION   307511 non-null  int64  
 34  LIVE_REGION_NOT_WORK_REGION  307511 non-null  int64  
 35  REG_CITY_NOT_LIVE_CITY       307511 non-null  int64  
 36  REG_CITY_NOT_WORK_CITY       307511 non-null  int64  
 37  LIVE_CITY_NOT_WORK_CITY      307511 non-null  int64  
 38  ORGANIZATION_TYPE            307511 non-null  object 
 39  OBS_30_CNT_SOCIAL_CIRCLE     306490 non-null  float64
 40  DEF_30_CNT_SOCIAL_CIRCLE     306490 non-null  float64
 41  OBS_60_CNT_SOCIAL_CIRCLE     306490 non-null  float64
 42  DEF_60_CNT_SOCIAL_CIRCLE     306490 non-null  float64
 43  DAYS_LAST_PHONE_CHANGE       307510 non-null  float64
 44  FLAG_DOCUMENT_2              307511 non-null  int64  
 45  FLAG_DOCUMENT_3              307511 non-null  int64  
 46  FLAG_DOCUMENT_4              307511 non-null  int64  
 47  FLAG_DOCUMENT_5              307511 non-null  int64  
 48  FLAG_DOCUMENT_6              307511 non-null  int64  
 49  FLAG_DOCUMENT_7              307511 non-null  int64  
 50  FLAG_DOCUMENT_8              307511 non-null  int64  
 51  FLAG_DOCUMENT_9              307511 non-null  int64  
 52  FLAG_DOCUMENT_10             307511 non-null  int64  
 53  FLAG_DOCUMENT_11             307511 non-null  int64  
 54  FLAG_DOCUMENT_12             307511 non-null  int64  
 55  FLAG_DOCUMENT_13             307511 non-null  int64  
 56  FLAG_DOCUMENT_14             307511 non-null  int64  
 57  FLAG_DOCUMENT_15             307511 non-null  int64  
 58  FLAG_DOCUMENT_16             307511 non-null  int64  
 59  FLAG_DOCUMENT_17             307511 non-null  int64  
 60  FLAG_DOCUMENT_18             307511 non-null  int64  
 61  FLAG_DOCUMENT_19             307511 non-null  int64  
 62  FLAG_DOCUMENT_20             307511 non-null  int64  
 63  FLAG_DOCUMENT_21             307511 non-null  int64  
 64  AMT_REQ_CREDIT_BUREAU_HOUR   265992 non-null  float64
 65  AMT_REQ_CREDIT_BUREAU_DAY    265992 non-null  float64
 66  AMT_REQ_CREDIT_BUREAU_WEEK   265992 non-null  float64
 67  AMT_REQ_CREDIT_BUREAU_MON    265992 non-null  float64
 68  AMT_REQ_CREDIT_BUREAU_QRT    265992 non-null  float64
 69  AMT_REQ_CREDIT_BUREAU_YEAR   265992 non-null  float64
dtypes: float64(18), int64(41), object(11)
memory usage: 164.2+ MB
<class 'NoneType'>


application_data['DAYS_BIRTH'] = abs(application_data['DAYS_BIRTH'])
application_data['DAYS_ID_PUBLISH'] = abs(application_data['DAYS_ID_PUBLISH'])
application_data['DAYS_ID_PUBLISH'] = abs(application_data['DAYS_ID_PUBLISH'])
application_data['DAYS_LAST_PHONE_CHANGE'] = abs(application_data['DAYS_LAST_PHONE_CHANGE'])


display("application_data")
display(application_data.head())

'application_data'


obj_dtypes = [i for i in application_data.select_dtypes(include=object).columns if i not in ["type"] ]
num_dtypes = [i for i in application_data.select_dtypes(include = np.number).columns if i not in ['SK_ID_CURR'] + [ 'TARGET']]


print(color.BOLD + color.PURPLE + 'Categorical Columns' + color.END, "\n")
for x in range(len(obj_dtypes)): 
    print(obj_dtypes[x])

Categorical Columns 

NAME_CONTRACT_TYPE
CODE_GENDER
FLAG_OWN_CAR
FLAG_OWN_REALTY
NAME_TYPE_SUITE
NAME_INCOME_TYPE
NAME_EDUCATION_TYPE
NAME_FAMILY_STATUS
NAME_HOUSING_TYPE
WEEKDAY_APPR_PROCESS_START
ORGANIZATION_TYPE


print(color.BOLD + color.PURPLE +"Numerical Columns" + color.END, "\n")
for x in range(len(num_dtypes)): 
    print(num_dtypes[x])

Numerical Columns 

CNT_CHILDREN
AMT_INCOME_TOTAL
AMT_CREDIT
AMT_ANNUITY
AMT_GOODS_PRICE
REGION_POPULATION_RELATIVE
DAYS_BIRTH
DAYS_EMPLOYED
DAYS_REGISTRATION
DAYS_ID_PUBLISH
FLAG_MOBIL
FLAG_EMP_PHONE
FLAG_WORK_PHONE
FLAG_CONT_MOBILE
FLAG_PHONE
FLAG_EMAIL
CNT_FAM_MEMBERS
REGION_RATING_CLIENT
REGION_RATING_CLIENT_W_CITY
HOUR_APPR_PROCESS_START
REG_REGION_NOT_LIVE_REGION
REG_REGION_NOT_WORK_REGION
LIVE_REGION_NOT_WORK_REGION
REG_CITY_NOT_LIVE_CITY
REG_CITY_NOT_WORK_CITY
LIVE_CITY_NOT_WORK_CITY
OBS_30_CNT_SOCIAL_CIRCLE
DEF_30_CNT_SOCIAL_CIRCLE
OBS_60_CNT_SOCIAL_CIRCLE
DEF_60_CNT_SOCIAL_CIRCLE
DAYS_LAST_PHONE_CHANGE
FLAG_DOCUMENT_2
FLAG_DOCUMENT_3
FLAG_DOCUMENT_4
FLAG_DOCUMENT_5
FLAG_DOCUMENT_6
FLAG_DOCUMENT_7
FLAG_DOCUMENT_8
FLAG_DOCUMENT_9
FLAG_DOCUMENT_10
FLAG_DOCUMENT_11
FLAG_DOCUMENT_12
FLAG_DOCUMENT_13
FLAG_DOCUMENT_14
FLAG_DOCUMENT_15
FLAG_DOCUMENT_16
FLAG_DOCUMENT_17
FLAG_DOCUMENT_18
FLAG_DOCUMENT_19
FLAG_DOCUMENT_20
FLAG_DOCUMENT_21
AMT_REQ_CREDIT_BUREAU_HOUR
AMT_REQ_CREDIT_BUREAU_DAY
AMT_REQ_CREDIT_BUREAU_WEEK
AMT_REQ_CREDIT_BUREAU_MON
AMT_REQ_CREDIT_BUREAU_QRT
AMT_REQ_CREDIT_BUREAU_YEAR


fig = plt.figure(figsize=(13,6))
plt.subplot(121)
application_data["CODE_GENDER"].value_counts().plot.pie(autopct = "%1.0f%%",colors = ["red","yellow"],startangle = 60,
                                                                        wedgeprops={"linewidth":2,"edgecolor":"k"},explode=[.05,0,0],shadow =True)
plt.title("Distribution of gender")
plt.show()


plt.figure(figsize=(14,7))
plt.subplot(121)
application_data["TARGET"].value_counts().plot.pie(autopct = "%1.0f%%",colors = sns.color_palette("prism",7),startangle = 60,labels=["repayer","defaulter"],
                                                                        wedgeprops={"linewidth":2,"edgecolor":"k"},explode=[.1,0],shadow =True)
plt.title("Distribution of target variable")

plt.subplot(122)
ax = application_data["TARGET"].value_counts().plot(kind="barh")

for i,j in enumerate(application_data["TARGET"].value_counts().values):
    ax.text(.7,i,j,weight = "bold",fontsize=20)

plt.title("Count of target variable")
plt.show()


application_data_x = application_data[[x for x in application_data.columns if x not in ["TARGET"]]]
previous_application_x = previous_application[[x for x in previous_application.columns if x not in ["TARGET"]]]
application_data_x["type"] = "application_data"
previous_application_x["type"] = "previous_application"
data = pd.concat([application_data_x,previous_application_x],axis=0)


plt.figure(figsize=(14,7))
plt.subplot(121)
data[data["type"] == "application_data"]["NAME_CONTRACT_TYPE"].value_counts().plot.pie(autopct = "%1.0f%%",colors = ["orange","red"],startangle = 60,
                                                                        wedgeprops={"linewidth":2,"edgecolor":"white"},shadow =True)
circ = plt.Circle((0,0),.7,color="white")
plt.gca().add_artist(circ)
plt.title("distribution of contract types in application_data")

plt.subplot(122)
data[data["type"] == "previous_application"]["NAME_CONTRACT_TYPE"].value_counts().plot.pie(autopct = "%1.2f%%",colors = ["red","yellow","green",'BLACK'],startangle = 60,
                                                                        wedgeprops={"linewidth":2,"edgecolor":"white"},shadow =True)
circ = plt.Circle((0,0),.7,color="white")
plt.gca().add_artist(circ)
plt.ylabel("")
plt.title("distribution of contract types in previous_application")
plt.show()

plt.show()


fig = plt.figure(figsize=(13,6))
plt.subplot(121)
data[data["type"] == "application_data"]["CODE_GENDER"].value_counts().plot.pie(autopct = "%1.0f%%",colors = ["red","yellow"],startangle = 60,
                                                                        wedgeprops={"linewidth":2,"edgecolor":"k"},explode=[.05,0,0],shadow =True)
plt.title("distribution of gender in application_data")
plt.show()


fig  = plt.figure(figsize=(13,6))
plt.subplot(121)
ax = sns.countplot("NAME_CONTRACT_TYPE",hue="CODE_GENDER",data=data[data["type"] == "application_data"],palette=["r","b","g"])
ax.set_facecolor("lightgrey")
ax.set_title("Distribution of Contract type by gender -application_data")


plt.show()


fig = plt.figure(figsize=(13,6))

plt.subplot(121)
data["FLAG_OWN_CAR"].value_counts().plot.pie(autopct = "%1.0f%%",colors = ["gold","orangered"],startangle = 60,
                                                                        wedgeprops={"linewidth":2,"edgecolor":"k"},explode=[.05,0],shadow =True)
plt.title("distribution of client owning a car")

plt.subplot(122)
data[data["FLAG_OWN_CAR"] == "Y"]["CODE_GENDER"].value_counts().plot.pie(autopct = "%1.0f%%",colors = ["b","orangered"],startangle = 90,
                                                                        wedgeprops={"linewidth":2,"edgecolor":"k"},explode=[.05,0,0],shadow =True)
plt.title("distribution of client owning a car by gender")

plt.show()


plt.figure(figsize=(13,6))
plt.subplot(121)
data["FLAG_OWN_REALTY"].value_counts().plot.pie(autopct = "%1.0f%%",colors = ["skyblue","gold"],startangle = 90,
                                              wedgeprops={"linewidth":2,"edgecolor":"k"},explode=[0.05,0],shadow =True)
plt.title("Distribution of client owns a house or flat")

plt.subplot(122)
data[data["FLAG_OWN_REALTY"] == "Y"]["CODE_GENDER"].value_counts().plot.pie(autopct = "%1.0f%%",colors = ["orangered","b"],startangle = 90,
                                                                        wedgeprops={"linewidth":2,"edgecolor":"k"},explode=[.05,0,0],shadow =True)
plt.title("Distribution of client owning a house or flat by gender")
plt.show()


fig = plt.figure(figsize=(12,10))
plt.subplot(211)
sns.countplot(application_data["CNT_CHILDREN"],palette="Set1",hue=application_data["TARGET"])
plt.legend(loc="upper center")
plt.title(" Distribution of Number of children client has  by repayment status")
plt.subplot(212)
sns.countplot(application_data["CNT_FAM_MEMBERS"],palette="Set1",hue=application_data["TARGET"])
plt.legend(loc="upper center")
plt.title(" Distribution of Number of family members client has  by repayment status")
fig.set_facecolor("lightblue")


default = application_data[application_data["TARGET"]==1][[ 'NAME_CONTRACT_TYPE', 'CODE_GENDER','FLAG_OWN_CAR', 'FLAG_OWN_REALTY']]
non_default = application_data[application_data["TARGET"]==0][[ 'NAME_CONTRACT_TYPE', 'CODE_GENDER','FLAG_OWN_CAR', 'FLAG_OWN_REALTY']]

d_cols = ['NAME_CONTRACT_TYPE', 'CODE_GENDER','FLAG_OWN_CAR', 'FLAG_OWN_REALTY']
d_length = len(d_cols)

fig = plt.figure(figsize=(16,4))
for i,j in itertools.zip_longest(d_cols,range(d_length)):
    plt.subplot(1,4,j+1)
    default[i].value_counts().plot.pie(autopct = "%1.0f%%",colors = sns.color_palette("prism"),startangle = 90,
                                        wedgeprops={"linewidth":1,"edgecolor":"white"},shadow =True)
    circ = plt.Circle((0,0),.7,color="white")
    plt.gca().add_artist(circ)
    plt.ylabel("")
    plt.title(i+"-Defaulter")


fig = plt.figure(figsize=(16,4))
for i,j in itertools.zip_longest(d_cols,range(d_length)):
    plt.subplot(1,4,j+1)
    non_default[i].value_counts().plot.pie(autopct = "%1.0f%%",colors = sns.color_palette("prism",3),startangle = 90,
                                           wedgeprops={"linewidth":1,"edgecolor":"white"},shadow =True)
    circ = plt.Circle((0,0),.7,color="white")
    plt.gca().add_artist(circ)
    plt.ylabel("")
    plt.title(i+"-Repayer")


cols = [ 'AMT_INCOME_TOTAL', 'AMT_CREDIT','AMT_ANNUITY', 'AMT_GOODS_PRICE']
length = len(cols)
cs = ["r","b","g","k"]

ax = plt.figure(figsize=(18,18))
ax.set_facecolor("lightgrey")
for i,j,k in itertools.zip_longest(cols,range(length),cs):
    plt.subplot(2,2,j+1)
    sns.distplot(data[data[i].notnull()][i],color=k)
    plt.axvline(data[i].mean(),label = "mean",linestyle="dashed",color="k")
    plt.legend(loc="best")
    plt.title(i)
    plt.subplots_adjust(hspace = .2)


df = application_data.groupby("TARGET")[cols].describe().transpose().reset_index()
df = df[df["level_1"].isin([ 'mean', 'std', 'min', 'max'])] 
df_x = df[["level_0","level_1",0]]
df_y = df[["level_0","level_1",1]]
df_x = df_x.rename(columns={'level_0':"amount_type", 'level_1':"statistic", 0:"amount"})
df_x["type"] = "REPAYER"
df_y = df_y.rename(columns={'level_0':"amount_type", 'level_1':"statistic", 1:"amount"})
df_y["type"] = "DEFAULTER"
df_new = pd.concat([df_x,df_y],axis = 0)

stat = df_new["statistic"].unique().tolist()
length = len(stat)

plt.figure(figsize=(13,15))

for i,j in itertools.zip_longest(stat,range(length)):
    plt.subplot(2,2,j+1)
    fig = sns.barplot(df_new[df_new["statistic"] == i]["amount_type"],df_new[df_new["statistic"] == i]["amount"],
                hue=df_new[df_new["statistic"] == i]["type"],palette=["g","r"])
    plt.title(i + "--Defaulters vs Non defaulters")
    plt.subplots_adjust(hspace = .4)
    fig.set_facecolor("lightgrey")


cols = [ 'AMT_INCOME_TOTAL', 'AMT_CREDIT','AMT_ANNUITY', 'AMT_GOODS_PRICE']

df1 = data.groupby("CODE_GENDER")[cols].mean().transpose().reset_index()

df_f   = df1[["index","F"]]
df_f   = df_f.rename(columns={'index':"amt_type", 'F':"amount"})
df_f["gender"] = "FEMALE"
df_m   = df1[["index","M"]]
df_m   = df_m.rename(columns={'index':"amt_type", 'M':"amount"})
df_m["gender"] = "MALE"
df_xna = df1[["index","XNA"]]
df_xna = df_xna.rename(columns={'index':"amt_type", 'XNA':"amount"})
df_xna["gender"] = "XNA"

df_gen = pd.concat([df_m,df_f,df_xna],axis=0)

plt.figure(figsize=(12,5))
ax = sns.barplot("amt_type","amount",data=df_gen,hue="gender",palette="Set1")
plt.title("Average Income,credit,annuity & goods_price by gender")
plt.show()


fig = plt.figure(figsize=(10,8))
plt.scatter(application_data[application_data["TARGET"]==0]['AMT_ANNUITY'],application_data[application_data["TARGET"]==0]['AMT_CREDIT'],s=35,
            color="b",alpha=.5,label="REPAYER",linewidth=.5,edgecolor="k")
plt.scatter(application_data[application_data["TARGET"]==1]['AMT_ANNUITY'],application_data[application_data["TARGET"]==1]['AMT_CREDIT'],s=35,
            color="r",alpha=.2,label="DEFAULTER",linewidth=.5,edgecolor="k")
plt.legend(loc="best",prop={"size":15})
plt.xlabel("AMT_ANNUITY")
plt.ylabel("AMT_CREDIT")
plt.title("Scatter plot between credit amount and annuity amount")
plt.show()


amt = application_data[[ 'AMT_INCOME_TOTAL','AMT_CREDIT',
                         'AMT_ANNUITY', 'AMT_GOODS_PRICE',"TARGET"]]
amt = amt[(amt["AMT_GOODS_PRICE"].notnull()) & (amt["AMT_ANNUITY"].notnull())]
sns.pairplot(amt,hue="TARGET",palette=["b","r"])
plt.show()


plt.figure(figsize=(18,12))
plt.subplot(121)
sns.countplot(y=data["NAME_TYPE_SUITE"],
              palette="Set2",
              order=data["NAME_TYPE_SUITE"].value_counts().index[:5])
plt.title("Distribution of Suite type")

plt.subplot(122)
sns.countplot(y=data["NAME_TYPE_SUITE"],
              hue=data["CODE_GENDER"],palette="Set2",
              order=data["NAME_TYPE_SUITE"].value_counts().index[:5])
plt.ylabel("")
plt.title("Distribution of Suite type by gender")
plt.subplots_adjust(wspace = .4)


plt.figure(figsize=(18,12))
plt.subplot(121)
sns.countplot(y=data["NAME_INCOME_TYPE"],
              palette="Set2",
              order=data["NAME_INCOME_TYPE"].value_counts().index[:4])
plt.title("Distribution of client income type")

plt.subplot(122)
sns.countplot(y=data["NAME_INCOME_TYPE"],
              hue=data["CODE_GENDER"],
              palette="Set2",
              order=data["NAME_INCOME_TYPE"].value_counts().index[:4])
plt.ylabel("")
plt.title("Distribution of client income  type by gender")
plt.subplots_adjust(wspace = .4)


plt.figure(figsize=(25,25))
plt.subplot(121)
application_data[application_data["TARGET"]==0]["NAME_EDUCATION_TYPE"].value_counts().plot.pie(fontsize=12,autopct = "%1.0f%%",
                                                                                                 colors = sns.color_palette("Set1"),
                                              wedgeprops={"linewidth":2,"edgecolor":"white"},shadow =True)
circ = plt.Circle((0,0),.7,color="white")
plt.gca().add_artist(circ)
plt.title("Distribution of Education type for Repayers",color="b")

plt.subplot(122)
application_data[application_data["TARGET"]==1]["NAME_EDUCATION_TYPE"].value_counts().plot.pie(fontsize=12,autopct = "%1.0f%%",
                                                                                                 colors = sns.color_palette("Set1"),
                                              wedgeprops={"linewidth":2,"edgecolor":"white"},shadow =True)
circ = plt.Circle((0,0),.7,color="white")
plt.gca().add_artist(circ)
plt.title("Distribution of Education type for Defaulters",color="b")
plt.ylabel("")
plt.show()


edu = data.groupby(['NAME_EDUCATION_TYPE','NAME_INCOME_TYPE'])['AMT_INCOME_TOTAL'].mean().reset_index().sort_values(by='AMT_INCOME_TOTAL',ascending=False)
fig = plt.figure(figsize=(13,7))
ax = sns.barplot('NAME_INCOME_TYPE','AMT_INCOME_TOTAL',data=edu,hue='NAME_EDUCATION_TYPE',palette="seismic")
ax.set_facecolor("k")
plt.title(" Average Earnings by different professions and education types")
plt.show()


plt.figure(figsize=(16,8))
plt.subplot(121)
application_data[application_data["TARGET"]==0]["NAME_FAMILY_STATUS"].value_counts().plot.pie(autopct = "%1.0f%%",
                                                             startangle=120,colors = sns.color_palette("Set2",7),
                                              wedgeprops={"linewidth":2,"edgecolor":"white"},shadow =True,explode=[0,.07,0,0,0,0])

plt.title("Distribution of Family status for Repayers",color="b")

plt.subplot(122)
application_data[application_data["TARGET"]==1]["NAME_FAMILY_STATUS"].value_counts().plot.pie(autopct = "%1.0f%%",
                                                    startangle=120,colors = sns.color_palette("Set2",7),
                                              wedgeprops={"linewidth":2,"edgecolor":"white"},shadow =True,explode=[0,.07,0,0,0])


plt.title("Distribution of Family status for Defaulters",color="b")
plt.ylabel("")
plt.show()


plt.figure(figsize=(20,20))
plt.subplot(121)
application_data[application_data["TARGET"]==0]["NAME_HOUSING_TYPE"].value_counts().plot.pie(autopct = "%1.0f%%",fontsize=10,
                                                             colors = sns.color_palette("Spectral"),
                                              wedgeprops={"linewidth":2,"edgecolor":"white"},shadow =True)

plt.title("Distribution of housing type  for Repayer",color="b")

plt.subplot(122)
application_data[application_data["TARGET"]==1]["NAME_HOUSING_TYPE"].value_counts().plot.pie(autopct = "%1.0f%%",fontsize=10,
                                                    colors = sns.color_palette("Spectral"),
                                              wedgeprops={"linewidth":2,"edgecolor":"white"},shadow =True)


plt.title("Distribution of housing type for Defaulters",color="b")
plt.ylabel("")
plt.show()


fig = plt.figure(figsize=(13,8))

plt.subplot(121)
sns.violinplot(y=application_data[application_data["TARGET"]==0]["REGION_POPULATION_RELATIVE"]
               ,x=application_data[application_data["TARGET"]==0]["NAME_CONTRACT_TYPE"],
               palette="Set1")
plt.title("Distribution of region population for Non Default loans",color="b")
plt.subplot(122)
sns.violinplot(y = application_data[application_data["TARGET"]==1]["REGION_POPULATION_RELATIVE"]
               ,x=application_data[application_data["TARGET"]==1]["NAME_CONTRACT_TYPE"]
               ,palette="Set1")
plt.title("Distribution of region population  for  Default loans",color="b")

plt.subplots_adjust(wspace = .2)
fig.set_facecolor("lightgrey")


import matplotlib.pyplot as plt
import seaborn as sns

fig = plt.figure(figsize=(13, 15))

plt.subplot(221)
sns.distplot(application_data[application_data["TARGET"] == 0]["DAYS_BIRTH"], color="b")
plt.title("Age Distribution of repayers")

plt.subplot(222)
sns.distplot(application_data[application_data["TARGET"] == 1]["DAYS_BIRTH"], color="r")
plt.title("Age Distribution of defaulters")

plt.subplot(223)
sns.boxplot(x="TARGET", y="DAYS_BIRTH", hue="CODE_GENDER", data=application_data, palette=["b", "grey", "m"])
plt.axhline(application_data["DAYS_BIRTH"].mean(), linestyle="dashed", color="k", label="average age of client")
plt.legend(loc="lower right")
plt.title("Client age vs Loan repayment status (hue=gender)")

plt.subplot(224)
sns.boxplot(x="TARGET", y="DAYS_BIRTH", hue="NAME_CONTRACT_TYPE", data=application_data, palette=["r", "g"])
plt.axhline(application_data["DAYS_BIRTH"].mean(), linestyle="dashed", color="k", label="average age of client")
plt.legend(loc="lower right")
plt.title("Client age vs Loan repayment status (hue=contract type)")

plt.subplots_adjust(wspace=.2, hspace=.3)

fig.set_facecolor("lightgrey")
plt.show()


fig = plt.figure(figsize=(13,5))

plt.subplot(121)
sns.distplot(application_data[application_data["TARGET"]==0]["DAYS_EMPLOYED"],color="b")
plt.title("days employed distribution of repayers")

plt.subplot(122)
sns.distplot(application_data[application_data["TARGET"]==1]["DAYS_EMPLOYED"],color="r")
plt.title("days employed distribution of defaulters")

fig.set_facecolor("ghostwhite")


fig = plt.figure(figsize=(13,5))

plt.subplot(121)
sns.distplot(application_data[application_data["TARGET"]==0]["DAYS_REGISTRATION"],color="b")
plt.title("registration days distribution of repayers")

plt.subplot(122)
sns.distplot(application_data[application_data["TARGET"]==1]["DAYS_REGISTRATION"],color="r")
plt.title("registration days distribution of defaulter")

fig.set_facecolor("ghostwhite")


x   = application_data[['FLAG_MOBIL', 'FLAG_EMP_PHONE', 'FLAG_WORK_PHONE', 'FLAG_CONT_MOBILE',
       'FLAG_PHONE', 'FLAG_EMAIL',"TARGET"]]
x["TARGET"] = x["TARGET"].replace({0:"repayers",1:"defaulters"})
x  = x.replace({1:"YES",0:"NO"})

cols = ['FLAG_MOBIL', 'FLAG_EMP_PHONE', 'FLAG_WORK_PHONE', 'FLAG_CONT_MOBILE',
       'FLAG_PHONE', 'FLAG_EMAIL']
length = len(cols)

fig = plt.figure(figsize=(15,12))
fig.set_facecolor("lightgrey")

for i,j in itertools.zip_longest(cols,range(length)):
    plt.subplot(2,3,j+1)
    sns.countplot(x[i],hue=x["TARGET"],palette=["r","g"])
    plt.title(i,color="b")


fig = plt.figure(figsize=(13,13))
plt.subplot(221)
application_data[application_data["TARGET"]==0]["REGION_RATING_CLIENT"].value_counts().plot.pie(autopct = "%1.0f%%",fontsize=12,
                                                             colors = sns.color_palette("Pastel1"),
                                              wedgeprops={"linewidth":2,"edgecolor":"white"},shadow =True)

plt.title("Distribution of region rating  for Repayers",color="b")

plt.subplot(222)
application_data[application_data["TARGET"]==1]["REGION_RATING_CLIENT"].value_counts().plot.pie(autopct = "%1.0f%%",fontsize=12,
                                                    colors = sns.color_palette("Pastel1"),
                                              wedgeprops={"linewidth":2,"edgecolor":"white"},shadow =True)


plt.title("Distribution of region rating  for Defaulters",color="b")
plt.ylabel("")

plt.subplot(223)
application_data[application_data["TARGET"]==0]["REGION_RATING_CLIENT_W_CITY"].value_counts().plot.pie(autopct = "%1.0f%%",fontsize=12,
                                                             colors = sns.color_palette("Paired"),
                                              wedgeprops={"linewidth":2,"edgecolor":"white"},shadow =True)

plt.title("Distribution of city region rating   for Repayers",color="b")

plt.subplot(224)
application_data[application_data["TARGET"]==1]["REGION_RATING_CLIENT_W_CITY"].value_counts().plot.pie(autopct = "%1.0f%%",fontsize=12,
                                                    colors = sns.color_palette("Paired"),
                                              wedgeprops={"linewidth":2,"edgecolor":"white"},shadow =True)


plt.title("Distribution of city region rating  for Defaulters",color="b")
plt.ylabel("")
fig.set_facecolor("ivory")


day = application_data.groupby("TARGET").agg({"WEEKDAY_APPR_PROCESS_START": "value_counts"})
day = day.rename(columns={"WEEKDAY_APPR_PROCESS_START": "value_counts"}).reset_index()
day_0 = day[:7]
day_1 = day[7:]
day_0["percentage"] = day_0["value_counts"] * 100 / day_0["value_counts"].sum()
day_1["percentage"] = day_1["value_counts"] * 100 / day_1["value_counts"].sum()
days = pd.concat([day_0, day_1], axis=0)

# Create a new column based on the "TARGET" values
days["TARGET"] = days["TARGET"].map({1: "defaulters", 0: "repayers"})

fig = plt.figure(figsize=(13, 15))
plt.subplot(211)
order = ['SUNDAY', 'MONDAY', 'TUESDAY', 'WEDNESDAY', 'THURSDAY', 'FRIDAY', 'SATURDAY']
ax = sns.barplot("WEEKDAY_APPR_PROCESS_START", "percentage", data=days,
                hue="TARGET", order=order, palette="prism")
ax.set_facecolor("k")
ax.set_title("Peak days for applying loans (defaulters vs repayers)")

hr = application_data.groupby("TARGET").agg({"HOUR_APPR_PROCESS_START": "value_counts"})
hr = hr.rename(columns={"HOUR_APPR_PROCESS_START": "value_counts"}).reset_index()
hr_0 = hr[hr["TARGET"] == 0]
hr_1 = hr[hr["TARGET"] == 1]
hr_0["percentage"] = hr_0["value_counts"] * 100 / hr_0["value_counts"].sum()
hr_1["percentage"] = hr_1["value_counts"] * 100 / hr_1["value_counts"].sum()
hrs = pd.concat([hr_0, hr_1], axis=0)

# Create a new column based on the "TARGET" values
hrs["TARGET"] = hrs["TARGET"].map({1: "defaulters", 0: "repayers"})

hrs = hrs.sort_values(by="HOUR_APPR_PROCESS_START", ascending=True)

plt.subplot(212)
ax1 = sns.pointplot("HOUR_APPR_PROCESS_START", "percentage", data=hrs, hue="TARGET", palette="prism")
ax1.set_facecolor("k")
ax1.set_title("Peak hours for applying loans (defaulters vs repayers")
fig.set_facecolor("snow")


org = application_data.groupby("TARGET").agg({"ORGANIZATION_TYPE":"value_counts"})
org = org.rename(columns = {"ORGANIZATION_TYPE":"value_counts"}).reset_index()
org_0 = org[org["TARGET"] == 0]
org_1 = org[org["TARGET"] == 1]
org_0["percentage"] = org_0["value_counts"]*100/org_0["value_counts"].sum()
org_1["percentage"] = org_1["value_counts"]*100/org_1["value_counts"].sum()

organization = pd.concat([org_0,org_1],axis=0)
organization = organization.sort_values(by="ORGANIZATION_TYPE",ascending=True)

organization["TARGET"] = organization["TARGET"].replace({0:"repayers",1:"defaulters"})

organization
plt.figure(figsize=(13,7))
ax = sns.pointplot("ORGANIZATION_TYPE","percentage",
                   data=organization,hue="TARGET",palette=["b","r"])
plt.xticks(rotation=90)
plt.grid(True,alpha=.3)
ax.set_facecolor("k")
ax.set_title("Distribution in organization types for repayers and defaulters")
plt.show()


fig = plt.figure(figsize=(20,20))
plt.subplot(421)
sns.boxplot(data=application_data,x='TARGET',y='OBS_30_CNT_SOCIAL_CIRCLE',
            hue="TARGET", palette="Set3")
plt.title("Client's social surroundings with observable 30 DPD (days past due) def",color="b")
plt.subplot(422)
sns.boxplot(data=application_data,x='TARGET',y='DEF_30_CNT_SOCIAL_CIRCLE',
            hue="TARGET", palette="Set3")
plt.title("Client's social surroundings defaulted on 30 DPD (days past due)",color="b")
plt.subplot(423)
sns.boxplot(data=application_data,x='TARGET',y='OBS_60_CNT_SOCIAL_CIRCLE',
            hue="TARGET", palette="Set3")
plt.title("Client's social surroundings with observable 60 DPD (days past due) default",color="b")
plt.subplot(424)
sns.boxplot(data=application_data,x='TARGET',y='DEF_60_CNT_SOCIAL_CIRCLE',
            hue="TARGET", palette="Set3")
plt.title("Client's social surroundings defaulted on 60 DPD (days past due)",color="b")
fig.set_facecolor("ghostwhite")


plt.figure(figsize=(13, 7))
plt.subplot(121)
ax = sns.violinplot(application_data["TARGET"],
                    application_data["DAYS_LAST_PHONE_CHANGE"], palette=["g", "r"])
ax.set_facecolor("oldlace")
ax.set_title("Days before application client changed phone - Violin Plot")
plt.subplot(122)
ax1 = sns.boxplot(x=application_data["TARGET"],
                  y=application_data["DAYS_LAST_PHONE_CHANGE"], palette=["g", "r"])
ax1.set_facecolor("oldlace")
ax1.set_ylabel("")
ax1.set_title("Days before application client changed phone - Box Plot")
plt.subplots_adjust(wspace=0.2)


cols = [ 'FLAG_DOCUMENT_2', 'FLAG_DOCUMENT_3',
       'FLAG_DOCUMENT_4', 'FLAG_DOCUMENT_5', 'FLAG_DOCUMENT_6',
       'FLAG_DOCUMENT_7', 'FLAG_DOCUMENT_8', 'FLAG_DOCUMENT_9',
       'FLAG_DOCUMENT_10', 'FLAG_DOCUMENT_11', 'FLAG_DOCUMENT_12',
       'FLAG_DOCUMENT_13', 'FLAG_DOCUMENT_14', 'FLAG_DOCUMENT_15',
       'FLAG_DOCUMENT_16', 'FLAG_DOCUMENT_17', 'FLAG_DOCUMENT_18',
       'FLAG_DOCUMENT_19', 'FLAG_DOCUMENT_20', 'FLAG_DOCUMENT_21']

df_flag = application_data[cols+["TARGET"]]

length = len(cols)

df_flag["TARGET"] = df_flag["TARGET"].replace({1:"defaulter",0:"repayer"})

fig = plt.figure(figsize=(13,24))
fig.set_facecolor("lightgrey")
for i,j in itertools.zip_longest(cols,range(length)):
    plt.subplot(5,4,j+1)
    ax = sns.countplot(df_flag[i],hue=df_flag["TARGET"],palette=["r","b"])
    plt.yticks(fontsize=5)
    plt.xlabel("")
    plt.title(i)
    ax.set_facecolor("k")


cols = ['AMT_REQ_CREDIT_BUREAU_HOUR', 'AMT_REQ_CREDIT_BUREAU_DAY',
       'AMT_REQ_CREDIT_BUREAU_WEEK', 'AMT_REQ_CREDIT_BUREAU_MON',
       'AMT_REQ_CREDIT_BUREAU_QRT', 'AMT_REQ_CREDIT_BUREAU_YEAR']
application_data.groupby("TARGET")[cols].max().transpose().plot(kind="barh",
                                                                 figsize=(10,5),width=.8)
plt.title("Maximum enquries made by defaulters and repayers")
application_data.groupby("TARGET")[cols].mean().transpose().plot(kind="barh",
                                                                  figsize=(10,5),width=.8)
plt.title("average enquries made by defaulters and repayers")
application_data.groupby("TARGET")[cols].std().transpose().plot(kind="barh",
                                                                 figsize=(10,5),width=.8)
plt.title("standard deviation in enquries made by defaulters and repayers")
plt.show()


x = previous_application.groupby("SK_ID_CURR")["SK_ID_PREV"].count().reset_index()
plt.figure(figsize=(13,7))
ax = sns.distplot(x["SK_ID_PREV"],color="orange")
plt.axvline(x["SK_ID_PREV"].mean(),linestyle="dashed",color="r",label="average")
plt.axvline(x["SK_ID_PREV"].std(),linestyle="dashed",color="b",label="standard deviation")
plt.axvline(x["SK_ID_PREV"].max(),linestyle="dashed",color="g",label="maximum")
plt.legend(loc="best")
plt.title("Current loan id having previous loan applications")
ax.set_facecolor("k")


pip install squarify

Defaulting to user installation because normal site-packages is not writeable
Collecting squarify
  Downloading squarify-0.4.3-py3-none-any.whl (4.3 kB)
Installing collected packages: squarify
Successfully installed squarify-0.4.3
Note: you may need to restart the kernel to use updated packages.


cnts = previous_application["NAME_CONTRACT_TYPE"].value_counts()
import squarify
plt.figure(figsize=(8,6))
squarify.plot(cnts.values,label=cnts.keys(),value=cnts.values,linewidth=2,edgecolor="k",alpha=.8,color=sns.color_palette("Set1"))
plt.axis("off")
plt.title("Contaract types in previous applications")
plt.show()

---------------------------------------------------------------------------
ModuleNotFoundError                       Traceback (most recent call last)
~\AppData\Local\Temp\ipykernel_13572\2131491753.py in <module>
      1 cnts = previous_application["NAME_CONTRACT_TYPE"].value_counts()
----> 2 import squarify
      3 plt.figure(figsize=(8,6))
      4 squarify.plot(cnts.values,label=cnts.keys(),value=cnts.values,linewidth=2,edgecolor="k",alpha=.8,color=sns.color_palette("Set1"))
      5 plt.axis("off")

ModuleNotFoundError: No module named 'squarify'


plt.figure(figsize=(20,20))
plt.subplot(211)
ax = sns.kdeplot(previous_application["AMT_APPLICATION"],color="b",linewidth=3)
ax = sns.kdeplot(previous_application[previous_application["AMT_CREDIT"].notnull()]["AMT_CREDIT"],color="r",linewidth=3)
plt.axvline(previous_application[previous_application["AMT_CREDIT"].notnull()]["AMT_CREDIT"].mean(),color="r",linestyle="dashed",label="AMT_APPLICATION_MEAN")
plt.axvline(previous_application["AMT_APPLICATION"].mean(),color="b",linestyle="dashed",label="AMT_APPLICATION_MEAN")
plt.legend(loc="best")
plt.title("Previous loan amounts applied and loan amounts credited.")
ax.set_facecolor("k")

plt.subplot(212)
diff = (previous_application["AMT_CREDIT"] - previous_application["AMT_APPLICATION"]).reset_index()
diff = diff[diff[0].notnull()]
ax1 = sns.kdeplot(diff[0],color="g",linewidth=3,label = "difference in amount requested by client and amount credited")
plt.axvline(diff[0].mean(),color="white",linestyle="dashed",label = "mean")
plt.title("difference in amount requested by client and amount credited")
ax1.legend(loc="best")
ax1.set_facecolor("k")


mn = previous_application.groupby("NAME_CONTRACT_TYPE")[["AMT_APPLICATION","AMT_CREDIT"]].mean().stack().reset_index()
tt = previous_application.groupby("NAME_CONTRACT_TYPE")[["AMT_APPLICATION","AMT_CREDIT"]].sum().stack().reset_index()
fig = plt.figure(figsize=(10,13))
fig.set_facecolor("ghostwhite")
plt.subplot(211)
ax = sns.barplot(0,"NAME_CONTRACT_TYPE",data=mn[:6],hue="level_1",palette="inferno")
ax.set_facecolor("k")
ax.set_xlabel("average amounts")
ax.set_title("Average amounts by contract types")

plt.subplot(212)
ax1 = sns.barplot(0,"NAME_CONTRACT_TYPE",data=tt[:6],hue="level_1",palette="magma")
ax1.set_facecolor("k")
ax1.set_xlabel("total amounts")
ax1.set_title("total amounts by contract types")
plt.subplots_adjust(hspace = .2)
plt.show()


plt.figure(figsize=(14,5))
plt.subplot(121)
previous_application.groupby("NAME_CONTRACT_TYPE")["AMT_ANNUITY"].sum().plot(kind="bar")
plt.xticks(rotation=0)
plt.title("Total annuity amount by contract types in previous applications")
plt.subplot(122)
previous_application.groupby("NAME_CONTRACT_TYPE")["AMT_ANNUITY"].mean().plot(kind="bar")
plt.title("average annuity amount by contract types in previous applications")
plt.xticks(rotation=0)
plt.show()


ax = pd.crosstab(previous_application["NAME_CONTRACT_TYPE"],previous_application["NAME_CONTRACT_STATUS"]).plot(kind="barh",figsize=(10,7),stacked=True)
plt.xticks(rotation =0)
plt.ylabel("count")
plt.title("Count of application status by application type")
ax.set_facecolor("k")


hr = pd.crosstab(previous_application["WEEKDAY_APPR_PROCESS_START"],previous_application["NAME_CONTRACT_STATUS"]).stack().reset_index()
plt.figure(figsize=(12,8))
ax = sns.pointplot(hr["WEEKDAY_APPR_PROCESS_START"],hr[0],hue=hr["NAME_CONTRACT_STATUS"],palette=["g","r","b","orange"],scale=1)
ax.set_facecolor("k")
ax.set_ylabel("count")
ax.set_title("Contract status by weekdays")
plt.grid(True,alpha=.2)


hr = pd.crosstab(previous_application["HOUR_APPR_PROCESS_START"],previous_application["NAME_CONTRACT_STATUS"]).stack().reset_index()
plt.figure(figsize=(12,8))
ax = sns.pointplot(hr["HOUR_APPR_PROCESS_START"],hr[0],hue=hr["NAME_CONTRACT_STATUS"],palette=["g","r","b","orange"],scale=1)
ax.set_facecolor("k")
ax.set_ylabel("count")
ax.set_title("Contract status by day hours.")
plt.grid(True,alpha=.2)


hr = pd.crosstab(previous_application["HOUR_APPR_PROCESS_START"],previous_application["WEEKDAY_APPR_PROCESS_START"]).stack().reset_index()
plt.figure(figsize=(12,8))
ax = sns.pointplot(hr["HOUR_APPR_PROCESS_START"],hr[0],hue=hr["WEEKDAY_APPR_PROCESS_START"],palette=["g","r","b","orange"],scale=1)
ax.set_facecolor("k")
ax.set_ylabel("count")
ax.set_title("Peak hours for week days")
plt.grid(True,alpha=.2)


previous_application[["NAME_CASH_LOAN_PURPOSE","NAME_CONTRACT_STATUS"]]
purpose = pd.crosstab(previous_application["NAME_CASH_LOAN_PURPOSE"],previous_application["NAME_CONTRACT_STATUS"])
purpose["a"] = (purpose["Approved"]*100)/(purpose["Approved"]+purpose["Canceled"]+purpose["Refused"]+purpose["Unused offer"])
purpose["c"] = (purpose["Canceled"]*100)/(purpose["Approved"]+purpose["Canceled"]+purpose["Refused"]+purpose["Unused offer"])
purpose["r"] = (purpose["Refused"]*100)/(purpose["Approved"]+purpose["Canceled"]+purpose["Refused"]+purpose["Unused offer"])
purpose["u"] = (purpose["Unused offer"]*100)/(purpose["Approved"]+purpose["Canceled"]+purpose["Refused"]+purpose["Unused offer"])
purpose_new = purpose[["a","c","r","u"]]
purpose_new = purpose_new.stack().reset_index()
purpose_new["NAME_CONTRACT_STATUS"] = purpose_new["NAME_CONTRACT_STATUS"].replace({"a":"accepted_percentage","c":"cancelled_percentage",
                                                               "r":"refused_percentage","u":"unused_percentage"})

lst = purpose_new["NAME_CONTRACT_STATUS"].unique().tolist()
length = len(lst)
cs = ["lime","orange","r","b"]

fig = plt.figure(figsize=(14,18))
fig.set_facecolor("lightgrey")
for i,j,k in itertools.zip_longest(lst,range(length),cs):
    plt.subplot(2,2,j+1)
    dat = purpose_new[purpose_new["NAME_CONTRACT_STATUS"] == i]
    ax = sns.barplot(0,"NAME_CASH_LOAN_PURPOSE",data=dat.sort_values(by=0,ascending=False),color=k)
    plt.ylabel("")
    plt.xlabel("percentage")
    plt.title(i+" by purpose")
    plt.subplots_adjust(wspace = .7)
    ax.set_facecolor("k")


plt.figure(figsize=(13,6))
sns.violinplot(y= previous_application["DAYS_DECISION"],
               x = previous_application["NAME_CONTRACT_STATUS"],palette=["r","g","b","y"])
plt.axhline(previous_application[previous_application["NAME_CONTRACT_STATUS"] == "Approved"]["DAYS_DECISION"].mean(),
            color="r",linestyle="dashed",label="accepted_average")
plt.axhline(previous_application[previous_application["NAME_CONTRACT_STATUS"] == "Refused"]["DAYS_DECISION"].mean(),
            color="g",linestyle="dashed",label="refused_average")
plt.axhline(previous_application[previous_application["NAME_CONTRACT_STATUS"] == "Cancelled"]["DAYS_DECISION"].mean(),color="b",
            linestyle="dashed",label="cancelled_average")
plt.axhline(previous_application[previous_application["NAME_CONTRACT_STATUS"] == "Unused offer"]["DAYS_DECISION"].mean(),color="y",
            linestyle="dashed",label="un used_average")
plt.legend(loc="best")

plt.title("Contract status relative to decision made about previous application.")
plt.show()


plt.figure(figsize=(8,12))
plt.subplot(211)
rej = previous_application["CODE_REJECT_REASON"].value_counts().reset_index()
ax = sns.barplot("CODE_REJECT_REASON","index",data=rej[:6],palette="husl")
for i,j in enumerate(np.around((rej["CODE_REJECT_REASON"][:6].values*100/(rej["CODE_REJECT_REASON"][:6].sum())))):
    ax.text(.7,i,j,weight="bold")
plt.xlabel("Top as percentage & Bottom as Count")
plt.ylabel("CODE_REJECT_REASON")
plt.title("Reasons for application rejections")

plt.subplot(212)
pay = previous_application["NAME_PAYMENT_TYPE"].value_counts().reset_index()
ax1 = sns.barplot("NAME_PAYMENT_TYPE","index",data=pay,palette="husl")
for i,j in enumerate(np.around((pay["NAME_PAYMENT_TYPE"].values*100/(pay["NAME_PAYMENT_TYPE"].sum())))):
    ax1.text(.7,i,j,weight="bold")
plt.xlabel("pTop as percentage & Bottom as Count")
plt.ylabel("NAME_PAYMENT_TYPE")
plt.title("Clients payment methods")
plt.subplots_adjust(hspace = .3)


plt.figure(figsize=(20,20))
plt.subplot(121)
previous_application["NAME_TYPE_SUITE"].value_counts().plot.pie(autopct = "%1.1f%%",fontsize=12,
                                                             colors = sns.color_palette("inferno"),
                                              wedgeprops={"linewidth":2,"edgecolor":"white"},shadow =True)
circ = plt.Circle((0,0),.7,color="white")
plt.gca().add_artist(circ)
plt.title("NAME_TYPE_SUITE")

plt.subplot(122)
previous_application["NAME_CLIENT_TYPE"].value_counts().plot.pie(autopct = "%1.1f%%",fontsize=12,
                                                             colors = sns.color_palette("inferno"),
                                              wedgeprops={"linewidth":2,"edgecolor":"white"},shadow =True)
circ = plt.Circle((0,0),.7,color="white")
plt.gca().add_artist(circ)
plt.title("NAME_CLIENT_TYPE")
plt.show()


goods = previous_application["NAME_GOODS_CATEGORY"].value_counts().reset_index()
goods["percentage"] = round(goods["NAME_GOODS_CATEGORY"]*100/goods["NAME_GOODS_CATEGORY"].sum(),2)
fig = plt.figure(figsize=(12,5))
ax = sns.pointplot("index","percentage",data=goods,color="yellow")
plt.xticks(rotation = 80)
plt.xlabel("NAME_GOODS_CATEGORY")
plt.ylabel("percentage")
plt.title("popular goods for applying loans")
ax.set_facecolor("k")
fig.set_facecolor('lightgrey')


plt.figure(figsize=(20,20))
plt.subplot(121)
previous_application["NAME_PORTFOLIO"].value_counts().plot.pie(autopct = "%1.1f%%",fontsize=12,
                                                             colors = sns.color_palette("prism",5),
                                              wedgeprops={"linewidth":2,"edgecolor":"white"},
                                                               shadow =True)
plt.title("previous applications portfolio")
plt.subplot(122)
previous_application["NAME_PRODUCT_TYPE"].value_counts().plot.pie(autopct = "%1.1f%%",fontsize=12,
                                                             colors = sns.color_palette("prism",3),
                                              wedgeprops={"linewidth":2,"edgecolor":"white"},
                                                                  shadow =True)
plt.title("previous applications product types")
plt.show()


app = pd.crosstab(previous_application["CHANNEL_TYPE"],previous_application["NAME_CONTRACT_STATUS"])
app1 = app
app1["approval_rate"] = app1["Approved"]*100/(app1["Approved"]+app1["Refused"]+app1["Canceled"])
app1["refused_rate"]  = app1["Refused"]*100/(app1["Approved"]+app1["Refused"]+app1["Canceled"])
app1["cacelled_rate"] = app1["Canceled"]*100/(app1["Approved"]+app1["Refused"]+app1["Canceled"])
app2 = app[["approval_rate","refused_rate","cacelled_rate"]]
ax = app2.plot(kind="barh",stacked=True,figsize=(10,7))
ax.set_facecolor("k")
ax.set_xlabel("percentage")
ax.set_title("approval,cancel and refusal rates by channel types")
plt.show()


fig = plt.figure(figsize=(13,5))
plt.subplot(121)
are = previous_application.groupby("SELLERPLACE_AREA")["AMT_CREDIT"].sum().reset_index()
are = are.sort_values(by ="AMT_CREDIT",ascending = False)
ax = sns.barplot(y= "AMT_CREDIT",x ="SELLERPLACE_AREA",data=are[:15],color="r")
ax.set_facecolor("k")
ax.set_title("Highest amount credited seller place areas")

plt.subplot(122)
sell = previous_application.groupby("NAME_SELLER_INDUSTRY")["AMT_CREDIT"].sum().reset_index().sort_values(by = "AMT_CREDIT",ascending = False)
ax1=sns.barplot(y = "AMT_CREDIT",x = "NAME_SELLER_INDUSTRY",data=sell,color="b")
ax1.set_facecolor("k")
ax1.set_title("Highest amount credited seller industrys")
plt.xticks(rotation=90)
plt.subplots_adjust(wspace = .5)
fig.set_facecolor("lightgrey")


plt.figure(figsize=(13,5))
ax = sns.countplot(previous_application["CNT_PAYMENT"],palette="Set1",order=previous_application["CNT_PAYMENT"].value_counts().index)
ax.set_facecolor("k")
plt.xticks(rotation = 90)
plt.title("popular terms of previous credit at application")
plt.show()


plt.figure(figsize=(10,8))
sns.countplot(y = previous_application["PRODUCT_COMBINATION"],order=previous_application["PRODUCT_COMBINATION"].value_counts().index)
plt.title("Detailed product combination of the previous application -count")
plt.show()


plt.figure(figsize=(12,6))
plt.subplot(121)
previous_application["NFLAG_INSURED_ON_APPROVAL"].value_counts().plot.pie(autopct = "%1.1f%%",fontsize=8,
                                                             colors = sns.color_palette("prism",4),
                                              wedgeprops={"linewidth":2,"edgecolor":"white"},shadow =True)
circ = plt.Circle((0,0),.7,color="white")
plt.gca().add_artist(circ)
plt.title("client requesting insurance")

plt.subplot(122)
previous_application["NAME_YIELD_GROUP"].value_counts().plot.pie(autopct = "%1.1f%%",fontsize=8,
                                                             colors = sns.color_palette("prism",4),
                                              wedgeprops={"linewidth":2,"edgecolor":"white"},shadow =True)
circ = plt.Circle((0,0),.7,color="white")
plt.gca().add_artist(circ)
plt.title("interest rates")
plt.show()


cols = ['DAYS_FIRST_DRAWING', 'DAYS_FIRST_DUE', 'DAYS_LAST_DUE_1ST_VERSION','DAYS_LAST_DUE', 'DAYS_TERMINATION']
plt.figure(figsize=(12,6))
sns.heatmap(previous_application[cols].describe()[1:].transpose(),
            annot=True,linewidth=2,linecolor="k",cmap=sns.color_palette("inferno"))
plt.show()


corrmat = application_data.corr() 
  
f, ax = plt.subplots(figsize =(8, 8)) 
sns.heatmap(corrmat, ax = ax, cmap ="rainbow") 
plt.show()


corrmat = previous_application.corr() 
  
f, ax = plt.subplots(figsize =(8, 8)) 
sns.heatmap(corrmat, ax = ax, cmap ="rainbow") 
plt.show()


corrmat = previous_application.corr() 
corrdf = corrmat.where(np.triu(np.ones(corrmat.shape), k=1).astype(np.bool))
corrdf = corrdf.unstack().reset_index()
corrdf.columns = ['Var1', 'Var2', 'Correlation']
corrdf.dropna(subset = ['Correlation'], inplace = True)
corrdf['Correlation'] = round(corrdf['Correlation'], 2)
corrdf['Correlation'] = abs(corrdf['Correlation'])
corrdf.sort_values(by = 'Correlation', ascending = False).head(10)


df_repayer = application_data[application_data['TARGET'] == 0]
df_defaulter = application_data[application_data['TARGET'] == 1]


corrmat = df_repayer.corr() 
corrdf = corrmat.where(np.triu(np.ones(corrmat.shape), k=1).astype(np.bool))
corrdf = corrdf.unstack().reset_index()
corrdf.columns = ['Var1', 'Var2', 'Correlation']
corrdf.dropna(subset = ['Correlation'], inplace = True)
corrdf['Correlation'] = round(corrdf['Correlation'], 2)
corrdf['Correlation'] = abs(corrdf['Correlation'])
corrdf.sort_values(by = 'Correlation', ascending = False).head(10)


corrmat = df_defaulter.corr() 
corrdf = corrmat.where(np.triu(np.ones(corrmat.shape), k=1).astype(np.bool))
corrdf = corrdf.unstack().reset_index()
corrdf.columns = ['Var1', 'Var2', 'Correlation']
corrdf.dropna(subset = ['Correlation'], inplace = True)
corrdf['Correlation'] = round(corrdf['Correlation'], 2)
corrdf['Correlation'] = abs(corrdf['Correlation'])
corrdf.sort_values(by = 'Correlation', ascending = False).head(10)


mergeddf =  pd.merge(application_data,previous_application,on='SK_ID_CURR')
mergeddf.head()


y = mergeddf.groupby('SK_ID_CURR').size()
dfA = mergeddf.groupby('SK_ID_CURR').agg({'TARGET': np.sum})
dfA['count'] = y
display(dfA.head(10))


dfA.sort_values(by = 'count',ascending=False).head(10)


df_repayer = dfA[dfA['TARGET'] == 0]
df_defaulter = dfA[dfA['TARGET'] == 1]


df_repayer.sort_values(by = 'count',ascending=False).head(10)


df_defaulter.sort_values(by = 'count',ascending=False).head(10)


mergeddf.isnull().sum()

SK_ID_CURR                      0     
TARGET                          0     
NAME_CONTRACT_TYPE_x            0     
CODE_GENDER                     0     
FLAG_OWN_CAR                    0     
FLAG_OWN_REALTY                 0     
CNT_CHILDREN                    0     
AMT_INCOME_TOTAL                0     
AMT_CREDIT_x                    0     
AMT_ANNUITY_x                   93    
AMT_GOODS_PRICE_x               1208  
NAME_TYPE_SUITE_x               3526  
NAME_INCOME_TYPE                0     
NAME_EDUCATION_TYPE             0     
NAME_FAMILY_STATUS              0     
NAME_HOUSING_TYPE               0     
REGION_POPULATION_RELATIVE      0     
DAYS_BIRTH                      0     
DAYS_EMPLOYED                   0     
DAYS_REGISTRATION               0     
DAYS_ID_PUBLISH                 0     
FLAG_MOBIL                      0     
FLAG_EMP_PHONE                  0     
FLAG_WORK_PHONE                 0     
FLAG_CONT_MOBILE                0     
FLAG_PHONE                      0     
FLAG_EMAIL                      0     
CNT_FAM_MEMBERS                 0     
REGION_RATING_CLIENT            0     
REGION_RATING_CLIENT_W_CITY     0     
WEEKDAY_APPR_PROCESS_START_x    0     
HOUR_APPR_PROCESS_START_x       0     
REG_REGION_NOT_LIVE_REGION      0     
REG_REGION_NOT_WORK_REGION      0     
LIVE_REGION_NOT_WORK_REGION     0     
REG_CITY_NOT_LIVE_CITY          0     
REG_CITY_NOT_WORK_CITY          0     
LIVE_CITY_NOT_WORK_CITY         0     
ORGANIZATION_TYPE               0     
OBS_30_CNT_SOCIAL_CIRCLE        3146  
DEF_30_CNT_SOCIAL_CIRCLE        3146  
OBS_60_CNT_SOCIAL_CIRCLE        3146  
DEF_60_CNT_SOCIAL_CIRCLE        3146  
DAYS_LAST_PHONE_CHANGE          0     
FLAG_DOCUMENT_2                 0     
FLAG_DOCUMENT_3                 0     
FLAG_DOCUMENT_4                 0     
FLAG_DOCUMENT_5                 0     
FLAG_DOCUMENT_6                 0     
FLAG_DOCUMENT_7                 0     
FLAG_DOCUMENT_8                 0     
FLAG_DOCUMENT_9                 0     
FLAG_DOCUMENT_10                0     
FLAG_DOCUMENT_11                0     
FLAG_DOCUMENT_12                0     
FLAG_DOCUMENT_13                0     
FLAG_DOCUMENT_14                0     
FLAG_DOCUMENT_15                0     
FLAG_DOCUMENT_16                0     
FLAG_DOCUMENT_17                0     
FLAG_DOCUMENT_18                0     
FLAG_DOCUMENT_19                0     
FLAG_DOCUMENT_20                0     
FLAG_DOCUMENT_21                0     
AMT_REQ_CREDIT_BUREAU_HOUR      163627
AMT_REQ_CREDIT_BUREAU_DAY       163627
AMT_REQ_CREDIT_BUREAU_WEEK      163627
AMT_REQ_CREDIT_BUREAU_MON       163627
AMT_REQ_CREDIT_BUREAU_QRT       163627
AMT_REQ_CREDIT_BUREAU_YEAR      163627
SK_ID_PREV                      0     
NAME_CONTRACT_TYPE_y            0     
AMT_ANNUITY_y                   307218
AMT_APPLICATION                 0     
AMT_CREDIT_y                    1     
AMT_GOODS_PRICE_y               319525
WEEKDAY_APPR_PROCESS_START_y    0     
HOUR_APPR_PROCESS_START_y       0     
FLAG_LAST_APPL_PER_CONTRACT     0     
NFLAG_LAST_APPL_IN_DAY          0     
NAME_CASH_LOAN_PURPOSE          0     
NAME_CONTRACT_STATUS            0     
DAYS_DECISION                   0     
NAME_PAYMENT_TYPE               0     
CODE_REJECT_REASON              0     
NAME_TYPE_SUITE_y               694672
NAME_CLIENT_TYPE                0     
NAME_GOODS_CATEGORY             0     
NAME_PORTFOLIO                  0     
NAME_PRODUCT_TYPE               0     
CHANNEL_TYPE                    0     
SELLERPLACE_AREA                0     
NAME_SELLER_INDUSTRY            0     
CNT_PAYMENT                     307213
NAME_YIELD_GROUP                0     
PRODUCT_COMBINATION             313   
DAYS_FIRST_DRAWING              561106
DAYS_FIRST_DUE                  561106
DAYS_LAST_DUE_1ST_VERSION       561106
DAYS_LAST_DUE                   561106
DAYS_TERMINATION                561106
NFLAG_INSURED_ON_APPROVAL       561106
dtype: int64


round(100*(mergeddf.isnull().sum()/len(mergeddf.index)), 2)

SK_ID_CURR                      0.00 
TARGET                          0.00 
NAME_CONTRACT_TYPE_x            0.00 
CODE_GENDER                     0.00 
FLAG_OWN_CAR                    0.00 
FLAG_OWN_REALTY                 0.00 
CNT_CHILDREN                    0.00 
AMT_INCOME_TOTAL                0.00 
AMT_CREDIT_x                    0.00 
AMT_ANNUITY_x                   0.01 
AMT_GOODS_PRICE_x               0.09 
NAME_TYPE_SUITE_x               0.25 
NAME_INCOME_TYPE                0.00 
NAME_EDUCATION_TYPE             0.00 
NAME_FAMILY_STATUS              0.00 
NAME_HOUSING_TYPE               0.00 
REGION_POPULATION_RELATIVE      0.00 
DAYS_BIRTH                      0.00 
DAYS_EMPLOYED                   0.00 
DAYS_REGISTRATION               0.00 
DAYS_ID_PUBLISH                 0.00 
FLAG_MOBIL                      0.00 
FLAG_EMP_PHONE                  0.00 
FLAG_WORK_PHONE                 0.00 
FLAG_CONT_MOBILE                0.00 
FLAG_PHONE                      0.00 
FLAG_EMAIL                      0.00 
CNT_FAM_MEMBERS                 0.00 
REGION_RATING_CLIENT            0.00 
REGION_RATING_CLIENT_W_CITY     0.00 
WEEKDAY_APPR_PROCESS_START_x    0.00 
HOUR_APPR_PROCESS_START_x       0.00 
REG_REGION_NOT_LIVE_REGION      0.00 
REG_REGION_NOT_WORK_REGION      0.00 
LIVE_REGION_NOT_WORK_REGION     0.00 
REG_CITY_NOT_LIVE_CITY          0.00 
REG_CITY_NOT_WORK_CITY          0.00 
LIVE_CITY_NOT_WORK_CITY         0.00 
ORGANIZATION_TYPE               0.00 
OBS_30_CNT_SOCIAL_CIRCLE        0.22 
DEF_30_CNT_SOCIAL_CIRCLE        0.22 
OBS_60_CNT_SOCIAL_CIRCLE        0.22 
DEF_60_CNT_SOCIAL_CIRCLE        0.22 
DAYS_LAST_PHONE_CHANGE          0.00 
FLAG_DOCUMENT_2                 0.00 
FLAG_DOCUMENT_3                 0.00 
FLAG_DOCUMENT_4                 0.00 
FLAG_DOCUMENT_5                 0.00 
FLAG_DOCUMENT_6                 0.00 
FLAG_DOCUMENT_7                 0.00 
FLAG_DOCUMENT_8                 0.00 
FLAG_DOCUMENT_9                 0.00 
FLAG_DOCUMENT_10                0.00 
FLAG_DOCUMENT_11                0.00 
FLAG_DOCUMENT_12                0.00 
FLAG_DOCUMENT_13                0.00 
FLAG_DOCUMENT_14                0.00 
FLAG_DOCUMENT_15                0.00 
FLAG_DOCUMENT_16                0.00 
FLAG_DOCUMENT_17                0.00 
FLAG_DOCUMENT_18                0.00 
FLAG_DOCUMENT_19                0.00 
FLAG_DOCUMENT_20                0.00 
FLAG_DOCUMENT_21                0.00 
AMT_REQ_CREDIT_BUREAU_HOUR      11.57
AMT_REQ_CREDIT_BUREAU_DAY       11.57
AMT_REQ_CREDIT_BUREAU_WEEK      11.57
AMT_REQ_CREDIT_BUREAU_MON       11.57
AMT_REQ_CREDIT_BUREAU_QRT       11.57
AMT_REQ_CREDIT_BUREAU_YEAR      11.57
SK_ID_PREV                      0.00 
NAME_CONTRACT_TYPE_y            0.00 
AMT_ANNUITY_y                   21.73
AMT_APPLICATION                 0.00 
AMT_CREDIT_y                    0.00 
AMT_GOODS_PRICE_y               22.60
WEEKDAY_APPR_PROCESS_START_y    0.00 
HOUR_APPR_PROCESS_START_y       0.00 
FLAG_LAST_APPL_PER_CONTRACT     0.00 
NFLAG_LAST_APPL_IN_DAY          0.00 
NAME_CASH_LOAN_PURPOSE          0.00 
NAME_CONTRACT_STATUS            0.00 
DAYS_DECISION                   0.00 
NAME_PAYMENT_TYPE               0.00 
CODE_REJECT_REASON              0.00 
NAME_TYPE_SUITE_y               49.14
NAME_CLIENT_TYPE                0.00 
NAME_GOODS_CATEGORY             0.00 
NAME_PORTFOLIO                  0.00 
NAME_PRODUCT_TYPE               0.00 
CHANNEL_TYPE                    0.00 
SELLERPLACE_AREA                0.00 
NAME_SELLER_INDUSTRY            0.00 
CNT_PAYMENT                     21.73
NAME_YIELD_GROUP                0.00 
PRODUCT_COMBINATION             0.02 
DAYS_FIRST_DRAWING              39.69
DAYS_FIRST_DUE                  39.69
DAYS_LAST_DUE_1ST_VERSION       39.69
DAYS_LAST_DUE                   39.69
DAYS_TERMINATION                39.69
NFLAG_INSURED_ON_APPROVAL       39.69
dtype: float64


mergeddf.head()


mergeddf.drop(['SK_ID_CURR'], 1, inplace = True)


mergeddf.head()


round(100*(mergeddf.isnull().sum()/len(mergeddf.index)), 2)

TARGET                          0.00 
NAME_CONTRACT_TYPE_x            0.00 
CODE_GENDER                     0.00 
FLAG_OWN_CAR                    0.00 
FLAG_OWN_REALTY                 0.00 
CNT_CHILDREN                    0.00 
AMT_INCOME_TOTAL                0.00 
AMT_CREDIT_x                    0.00 
AMT_ANNUITY_x                   0.01 
AMT_GOODS_PRICE_x               0.09 
NAME_TYPE_SUITE_x               0.25 
NAME_INCOME_TYPE                0.00 
NAME_EDUCATION_TYPE             0.00 
NAME_FAMILY_STATUS              0.00 
NAME_HOUSING_TYPE               0.00 
REGION_POPULATION_RELATIVE      0.00 
DAYS_BIRTH                      0.00 
DAYS_EMPLOYED                   0.00 
DAYS_REGISTRATION               0.00 
DAYS_ID_PUBLISH                 0.00 
FLAG_MOBIL                      0.00 
FLAG_EMP_PHONE                  0.00 
FLAG_WORK_PHONE                 0.00 
FLAG_CONT_MOBILE                0.00 
FLAG_PHONE                      0.00 
FLAG_EMAIL                      0.00 
CNT_FAM_MEMBERS                 0.00 
REGION_RATING_CLIENT            0.00 
REGION_RATING_CLIENT_W_CITY     0.00 
WEEKDAY_APPR_PROCESS_START_x    0.00 
HOUR_APPR_PROCESS_START_x       0.00 
REG_REGION_NOT_LIVE_REGION      0.00 
REG_REGION_NOT_WORK_REGION      0.00 
LIVE_REGION_NOT_WORK_REGION     0.00 
REG_CITY_NOT_LIVE_CITY          0.00 
REG_CITY_NOT_WORK_CITY          0.00 
LIVE_CITY_NOT_WORK_CITY         0.00 
ORGANIZATION_TYPE               0.00 
OBS_30_CNT_SOCIAL_CIRCLE        0.22 
DEF_30_CNT_SOCIAL_CIRCLE        0.22 
OBS_60_CNT_SOCIAL_CIRCLE        0.22 
DEF_60_CNT_SOCIAL_CIRCLE        0.22 
DAYS_LAST_PHONE_CHANGE          0.00 
FLAG_DOCUMENT_2                 0.00 
FLAG_DOCUMENT_3                 0.00 
FLAG_DOCUMENT_4                 0.00 
FLAG_DOCUMENT_5                 0.00 
FLAG_DOCUMENT_6                 0.00 
FLAG_DOCUMENT_7                 0.00 
FLAG_DOCUMENT_8                 0.00 
FLAG_DOCUMENT_9                 0.00 
FLAG_DOCUMENT_10                0.00 
FLAG_DOCUMENT_11                0.00 
FLAG_DOCUMENT_12                0.00 
FLAG_DOCUMENT_13                0.00 
FLAG_DOCUMENT_14                0.00 
FLAG_DOCUMENT_15                0.00 
FLAG_DOCUMENT_16                0.00 
FLAG_DOCUMENT_17                0.00 
FLAG_DOCUMENT_18                0.00 
FLAG_DOCUMENT_19                0.00 
FLAG_DOCUMENT_20                0.00 
FLAG_DOCUMENT_21                0.00 
AMT_REQ_CREDIT_BUREAU_HOUR      11.57
AMT_REQ_CREDIT_BUREAU_DAY       11.57
AMT_REQ_CREDIT_BUREAU_WEEK      11.57
AMT_REQ_CREDIT_BUREAU_MON       11.57
AMT_REQ_CREDIT_BUREAU_QRT       11.57
AMT_REQ_CREDIT_BUREAU_YEAR      11.57
SK_ID_PREV                      0.00 
NAME_CONTRACT_TYPE_y            0.00 
AMT_ANNUITY_y                   21.73
AMT_APPLICATION                 0.00 
AMT_CREDIT_y                    0.00 
AMT_GOODS_PRICE_y               22.60
WEEKDAY_APPR_PROCESS_START_y    0.00 
HOUR_APPR_PROCESS_START_y       0.00 
FLAG_LAST_APPL_PER_CONTRACT     0.00 
NFLAG_LAST_APPL_IN_DAY          0.00 
NAME_CASH_LOAN_PURPOSE          0.00 
NAME_CONTRACT_STATUS            0.00 
DAYS_DECISION                   0.00 
NAME_PAYMENT_TYPE               0.00 
CODE_REJECT_REASON              0.00 
NAME_TYPE_SUITE_y               49.14
NAME_CLIENT_TYPE                0.00 
NAME_GOODS_CATEGORY             0.00 
NAME_PORTFOLIO                  0.00 
NAME_PRODUCT_TYPE               0.00 
CHANNEL_TYPE                    0.00 
SELLERPLACE_AREA                0.00 
NAME_SELLER_INDUSTRY            0.00 
CNT_PAYMENT                     21.73
NAME_YIELD_GROUP                0.00 
PRODUCT_COMBINATION             0.02 
DAYS_FIRST_DRAWING              39.69
DAYS_FIRST_DUE                  39.69
DAYS_LAST_DUE_1ST_VERSION       39.69
DAYS_LAST_DUE                   39.69
DAYS_TERMINATION                39.69
NFLAG_INSURED_ON_APPROVAL       39.69
dtype: float64


enq_cs =['AMT_REQ_CREDIT_BUREAU_DAY', 'AMT_REQ_CREDIT_BUREAU_HOUR',
       'AMT_REQ_CREDIT_BUREAU_MON', 'AMT_REQ_CREDIT_BUREAU_QRT',
       'AMT_REQ_CREDIT_BUREAU_WEEK', 'AMT_REQ_CREDIT_BUREAU_YEAR']
for i in enq_cs:
    mergeddf[i] = mergeddf[i].fillna(0)


amt_cs = ["AMT_ANNUITY_y","AMT_GOODS_PRICE_y"]
for i in amt_cs:
    mergeddf[i] = mergeddf[i].fillna(mergeddf[i].mean())


cols = ["DAYS_FIRST_DRAWING","DAYS_FIRST_DUE","DAYS_LAST_DUE_1ST_VERSION",
        "DAYS_LAST_DUE","DAYS_TERMINATION",'CNT_PAYMENT']
for i in cols :
    mergeddf[i]  = mergeddf[i].fillna(mergeddf[i].median())


cols = ["NAME_TYPE_SUITE_y","NFLAG_INSURED_ON_APPROVAL"]
for i in cols :
    mergeddf[i]  = mergeddf[i].fillna(mergeddf[i].mode()[0])


mergeddf.dropna(inplace = True)


round(100*(mergeddf.isnull().sum()/len(mergeddf.index)), 2)

TARGET                          0.0
NAME_CONTRACT_TYPE_x            0.0
CODE_GENDER                     0.0
FLAG_OWN_CAR                    0.0
FLAG_OWN_REALTY                 0.0
CNT_CHILDREN                    0.0
AMT_INCOME_TOTAL                0.0
AMT_CREDIT_x                    0.0
AMT_ANNUITY_x                   0.0
AMT_GOODS_PRICE_x               0.0
NAME_TYPE_SUITE_x               0.0
NAME_INCOME_TYPE                0.0
NAME_EDUCATION_TYPE             0.0
NAME_FAMILY_STATUS              0.0
NAME_HOUSING_TYPE               0.0
REGION_POPULATION_RELATIVE      0.0
DAYS_BIRTH                      0.0
DAYS_EMPLOYED                   0.0
DAYS_REGISTRATION               0.0
DAYS_ID_PUBLISH                 0.0
FLAG_MOBIL                      0.0
FLAG_EMP_PHONE                  0.0
FLAG_WORK_PHONE                 0.0
FLAG_CONT_MOBILE                0.0
FLAG_PHONE                      0.0
FLAG_EMAIL                      0.0
CNT_FAM_MEMBERS                 0.0
REGION_RATING_CLIENT            0.0
REGION_RATING_CLIENT_W_CITY     0.0
WEEKDAY_APPR_PROCESS_START_x    0.0
HOUR_APPR_PROCESS_START_x       0.0
REG_REGION_NOT_LIVE_REGION      0.0
REG_REGION_NOT_WORK_REGION      0.0
LIVE_REGION_NOT_WORK_REGION     0.0
REG_CITY_NOT_LIVE_CITY          0.0
REG_CITY_NOT_WORK_CITY          0.0
LIVE_CITY_NOT_WORK_CITY         0.0
ORGANIZATION_TYPE               0.0
OBS_30_CNT_SOCIAL_CIRCLE        0.0
DEF_30_CNT_SOCIAL_CIRCLE        0.0
OBS_60_CNT_SOCIAL_CIRCLE        0.0
DEF_60_CNT_SOCIAL_CIRCLE        0.0
DAYS_LAST_PHONE_CHANGE          0.0
FLAG_DOCUMENT_2                 0.0
FLAG_DOCUMENT_3                 0.0
FLAG_DOCUMENT_4                 0.0
FLAG_DOCUMENT_5                 0.0
FLAG_DOCUMENT_6                 0.0
FLAG_DOCUMENT_7                 0.0
FLAG_DOCUMENT_8                 0.0
FLAG_DOCUMENT_9                 0.0
FLAG_DOCUMENT_10                0.0
FLAG_DOCUMENT_11                0.0
FLAG_DOCUMENT_12                0.0
FLAG_DOCUMENT_13                0.0
FLAG_DOCUMENT_14                0.0
FLAG_DOCUMENT_15                0.0
FLAG_DOCUMENT_16                0.0
FLAG_DOCUMENT_17                0.0
FLAG_DOCUMENT_18                0.0
FLAG_DOCUMENT_19                0.0
FLAG_DOCUMENT_20                0.0
FLAG_DOCUMENT_21                0.0
AMT_REQ_CREDIT_BUREAU_HOUR      0.0
AMT_REQ_CREDIT_BUREAU_DAY       0.0
AMT_REQ_CREDIT_BUREAU_WEEK      0.0
AMT_REQ_CREDIT_BUREAU_MON       0.0
AMT_REQ_CREDIT_BUREAU_QRT       0.0
AMT_REQ_CREDIT_BUREAU_YEAR      0.0
SK_ID_PREV                      0.0
NAME_CONTRACT_TYPE_y            0.0
AMT_ANNUITY_y                   0.0
AMT_APPLICATION                 0.0
AMT_CREDIT_y                    0.0
AMT_GOODS_PRICE_y               0.0
WEEKDAY_APPR_PROCESS_START_y    0.0
HOUR_APPR_PROCESS_START_y       0.0
FLAG_LAST_APPL_PER_CONTRACT     0.0
NFLAG_LAST_APPL_IN_DAY          0.0
NAME_CASH_LOAN_PURPOSE          0.0
NAME_CONTRACT_STATUS            0.0
DAYS_DECISION                   0.0
NAME_PAYMENT_TYPE               0.0
CODE_REJECT_REASON              0.0
NAME_TYPE_SUITE_y               0.0
NAME_CLIENT_TYPE                0.0
NAME_GOODS_CATEGORY             0.0
NAME_PORTFOLIO                  0.0
NAME_PRODUCT_TYPE               0.0
CHANNEL_TYPE                    0.0
SELLERPLACE_AREA                0.0
NAME_SELLER_INDUSTRY            0.0
CNT_PAYMENT                     0.0
NAME_YIELD_GROUP                0.0
PRODUCT_COMBINATION             0.0
DAYS_FIRST_DRAWING              0.0
DAYS_FIRST_DUE                  0.0
DAYS_LAST_DUE_1ST_VERSION       0.0
DAYS_LAST_DUE                   0.0
DAYS_TERMINATION                0.0
NFLAG_INSURED_ON_APPROVAL       0.0
dtype: float64


mergeddf.isnull().sum()

TARGET                          0
NAME_CONTRACT_TYPE_x            0
CODE_GENDER                     0
FLAG_OWN_CAR                    0
FLAG_OWN_REALTY                 0
CNT_CHILDREN                    0
AMT_INCOME_TOTAL                0
AMT_CREDIT_x                    0
AMT_ANNUITY_x                   0
AMT_GOODS_PRICE_x               0
NAME_TYPE_SUITE_x               0
NAME_INCOME_TYPE                0
NAME_EDUCATION_TYPE             0
NAME_FAMILY_STATUS              0
NAME_HOUSING_TYPE               0
REGION_POPULATION_RELATIVE      0
DAYS_BIRTH                      0
DAYS_EMPLOYED                   0
DAYS_REGISTRATION               0
DAYS_ID_PUBLISH                 0
FLAG_MOBIL                      0
FLAG_EMP_PHONE                  0
FLAG_WORK_PHONE                 0
FLAG_CONT_MOBILE                0
FLAG_PHONE                      0
FLAG_EMAIL                      0
CNT_FAM_MEMBERS                 0
REGION_RATING_CLIENT            0
REGION_RATING_CLIENT_W_CITY     0
WEEKDAY_APPR_PROCESS_START_x    0
HOUR_APPR_PROCESS_START_x       0
REG_REGION_NOT_LIVE_REGION      0
REG_REGION_NOT_WORK_REGION      0
LIVE_REGION_NOT_WORK_REGION     0
REG_CITY_NOT_LIVE_CITY          0
REG_CITY_NOT_WORK_CITY          0
LIVE_CITY_NOT_WORK_CITY         0
ORGANIZATION_TYPE               0
OBS_30_CNT_SOCIAL_CIRCLE        0
DEF_30_CNT_SOCIAL_CIRCLE        0
OBS_60_CNT_SOCIAL_CIRCLE        0
DEF_60_CNT_SOCIAL_CIRCLE        0
DAYS_LAST_PHONE_CHANGE          0
FLAG_DOCUMENT_2                 0
FLAG_DOCUMENT_3                 0
FLAG_DOCUMENT_4                 0
FLAG_DOCUMENT_5                 0
FLAG_DOCUMENT_6                 0
FLAG_DOCUMENT_7                 0
FLAG_DOCUMENT_8                 0
FLAG_DOCUMENT_9                 0
FLAG_DOCUMENT_10                0
FLAG_DOCUMENT_11                0
FLAG_DOCUMENT_12                0
FLAG_DOCUMENT_13                0
FLAG_DOCUMENT_14                0
FLAG_DOCUMENT_15                0
FLAG_DOCUMENT_16                0
FLAG_DOCUMENT_17                0
FLAG_DOCUMENT_18                0
FLAG_DOCUMENT_19                0
FLAG_DOCUMENT_20                0
FLAG_DOCUMENT_21                0
AMT_REQ_CREDIT_BUREAU_HOUR      0
AMT_REQ_CREDIT_BUREAU_DAY       0
AMT_REQ_CREDIT_BUREAU_WEEK      0
AMT_REQ_CREDIT_BUREAU_MON       0
AMT_REQ_CREDIT_BUREAU_QRT       0
AMT_REQ_CREDIT_BUREAU_YEAR      0
SK_ID_PREV                      0
NAME_CONTRACT_TYPE_y            0
AMT_ANNUITY_y                   0
AMT_APPLICATION                 0
AMT_CREDIT_y                    0
AMT_GOODS_PRICE_y               0
WEEKDAY_APPR_PROCESS_START_y    0
HOUR_APPR_PROCESS_START_y       0
FLAG_LAST_APPL_PER_CONTRACT     0
NFLAG_LAST_APPL_IN_DAY          0
NAME_CASH_LOAN_PURPOSE          0
NAME_CONTRACT_STATUS            0
DAYS_DECISION                   0
NAME_PAYMENT_TYPE               0
CODE_REJECT_REASON              0
NAME_TYPE_SUITE_y               0
NAME_CLIENT_TYPE                0
NAME_GOODS_CATEGORY             0
NAME_PORTFOLIO                  0
NAME_PRODUCT_TYPE               0
CHANNEL_TYPE                    0
SELLERPLACE_AREA                0
NAME_SELLER_INDUSTRY            0
CNT_PAYMENT                     0
NAME_YIELD_GROUP                0
PRODUCT_COMBINATION             0
DAYS_FIRST_DRAWING              0
DAYS_FIRST_DUE                  0
DAYS_LAST_DUE_1ST_VERSION       0
DAYS_LAST_DUE                   0
DAYS_TERMINATION                0
NFLAG_INSURED_ON_APPROVAL       0
dtype: int64


mergeddf.head()


# List of variables to map

varlist =  ['FLAG_OWN_CAR','FLAG_OWN_REALTY','FLAG_LAST_APPL_PER_CONTRACT']

# Defining the map function
def binary_map(x):
    return x.map({'Y': 1, "N": 0})

# Applying the function to the housing list
mergeddf[varlist] = mergeddf[varlist].apply(binary_map)
mergeddf.head()


mergeddf.drop(['SK_ID_PREV'], 1, inplace = True)
mergeddf.head()


mergeddf[['FLAG_OWN_CAR','FLAG_OWN_REALTY','FLAG_MOBIL',
 'FLAG_EMP_PHONE','FLAG_WORK_PHONE','FLAG_CONT_MOBILE',
 'FLAG_PHONE','FLAG_EMAIL','REGION_RATING_CLIENT',
 'REGION_RATING_CLIENT_W_CITY','REG_REGION_NOT_LIVE_REGION',
 'REG_REGION_NOT_WORK_REGION','LIVE_REGION_NOT_WORK_REGION',
 'REG_CITY_NOT_LIVE_CITY','REG_CITY_NOT_WORK_CITY','FLAG_DOCUMENT_2',
 'FLAG_DOCUMENT_3','FLAG_DOCUMENT_4','FLAG_DOCUMENT_5','FLAG_DOCUMENT_6',
 'FLAG_DOCUMENT_7','FLAG_DOCUMENT_8','FLAG_DOCUMENT_9',
 'FLAG_DOCUMENT_10','FLAG_DOCUMENT_11','FLAG_DOCUMENT_12','FLAG_DOCUMENT_13',
 'FLAG_DOCUMENT_14','FLAG_DOCUMENT_15','FLAG_DOCUMENT_16','FLAG_DOCUMENT_17',
 'FLAG_DOCUMENT_18','FLAG_DOCUMENT_19','FLAG_DOCUMENT_20','FLAG_DOCUMENT_21',
 'NFLAG_INSURED_ON_APPROVAL']]= mergeddf[['FLAG_OWN_CAR','FLAG_OWN_REALTY','FLAG_MOBIL',
                                        'FLAG_EMP_PHONE','FLAG_WORK_PHONE','FLAG_CONT_MOBILE',
                                        'FLAG_PHONE','FLAG_EMAIL','REGION_RATING_CLIENT',
                                        'REGION_RATING_CLIENT_W_CITY','REG_REGION_NOT_LIVE_REGION',
                                        'REG_REGION_NOT_WORK_REGION','LIVE_REGION_NOT_WORK_REGION',
                                        'REG_CITY_NOT_LIVE_CITY','REG_CITY_NOT_WORK_CITY','FLAG_DOCUMENT_2',
                                        'FLAG_DOCUMENT_3','FLAG_DOCUMENT_4','FLAG_DOCUMENT_5','FLAG_DOCUMENT_6',
                                        'FLAG_DOCUMENT_7','FLAG_DOCUMENT_8','FLAG_DOCUMENT_9',
                                        'FLAG_DOCUMENT_10','FLAG_DOCUMENT_11','FLAG_DOCUMENT_12','FLAG_DOCUMENT_13',
                                        'FLAG_DOCUMENT_14','FLAG_DOCUMENT_15','FLAG_DOCUMENT_16','FLAG_DOCUMENT_17',
                                        'FLAG_DOCUMENT_18','FLAG_DOCUMENT_19','FLAG_DOCUMENT_20','FLAG_DOCUMENT_21',
                                        'NFLAG_INSURED_ON_APPROVAL']].astype('category')


obj_dtypes = [i for i in mergeddf.select_dtypes(include=object).columns if i not in ["type"] ]
num_dtypes = [i for i in mergeddf.select_dtypes(include = np.number).columns if i not in [ 'TARGET']]


num_dtypes

['CNT_CHILDREN',
 'AMT_INCOME_TOTAL',
 'AMT_CREDIT_x',
 'AMT_ANNUITY_x',
 'AMT_GOODS_PRICE_x',
 'REGION_POPULATION_RELATIVE',
 'DAYS_BIRTH',
 'DAYS_EMPLOYED',
 'DAYS_REGISTRATION',
 'DAYS_ID_PUBLISH',
 'CNT_FAM_MEMBERS',
 'HOUR_APPR_PROCESS_START_x',
 'LIVE_CITY_NOT_WORK_CITY',
 'OBS_30_CNT_SOCIAL_CIRCLE',
 'DEF_30_CNT_SOCIAL_CIRCLE',
 'OBS_60_CNT_SOCIAL_CIRCLE',
 'DEF_60_CNT_SOCIAL_CIRCLE',
 'DAYS_LAST_PHONE_CHANGE',
 'AMT_REQ_CREDIT_BUREAU_HOUR',
 'AMT_REQ_CREDIT_BUREAU_DAY',
 'AMT_REQ_CREDIT_BUREAU_WEEK',
 'AMT_REQ_CREDIT_BUREAU_MON',
 'AMT_REQ_CREDIT_BUREAU_QRT',
 'AMT_REQ_CREDIT_BUREAU_YEAR',
 'AMT_ANNUITY_y',
 'AMT_APPLICATION',
 'AMT_CREDIT_y',
 'AMT_GOODS_PRICE_y',
 'HOUR_APPR_PROCESS_START_y',
 'FLAG_LAST_APPL_PER_CONTRACT',
 'NFLAG_LAST_APPL_IN_DAY',
 'DAYS_DECISION',
 'SELLERPLACE_AREA',
 'CNT_PAYMENT',
 'DAYS_FIRST_DRAWING',
 'DAYS_FIRST_DUE',
 'DAYS_LAST_DUE_1ST_VERSION',
 'DAYS_LAST_DUE',
 'DAYS_TERMINATION']


obj_dtypes

['NAME_CONTRACT_TYPE_x',
 'CODE_GENDER',
 'NAME_TYPE_SUITE_x',
 'NAME_INCOME_TYPE',
 'NAME_EDUCATION_TYPE',
 'NAME_FAMILY_STATUS',
 'NAME_HOUSING_TYPE',
 'WEEKDAY_APPR_PROCESS_START_x',
 'ORGANIZATION_TYPE',
 'NAME_CONTRACT_TYPE_y',
 'WEEKDAY_APPR_PROCESS_START_y',
 'NAME_CASH_LOAN_PURPOSE',
 'NAME_CONTRACT_STATUS',
 'NAME_PAYMENT_TYPE',
 'CODE_REJECT_REASON',
 'NAME_TYPE_SUITE_y',
 'NAME_CLIENT_TYPE',
 'NAME_GOODS_CATEGORY',
 'NAME_PORTFOLIO',
 'NAME_PRODUCT_TYPE',
 'CHANNEL_TYPE',
 'NAME_SELLER_INDUSTRY',
 'NAME_YIELD_GROUP',
 'PRODUCT_COMBINATION']


# Creating a dummy variable for some of the categorical variables and dropping the first one.
dummy1 = pd.get_dummies(mergeddf[['FLAG_OWN_CAR','FLAG_OWN_REALTY','FLAG_MOBIL',
                                  'FLAG_EMP_PHONE','FLAG_WORK_PHONE','FLAG_CONT_MOBILE',
                                  'FLAG_PHONE','FLAG_EMAIL','REGION_RATING_CLIENT',
                                  'REGION_RATING_CLIENT_W_CITY','REG_REGION_NOT_LIVE_REGION',
                                  'REG_REGION_NOT_WORK_REGION','LIVE_REGION_NOT_WORK_REGION',
                                  'REG_CITY_NOT_LIVE_CITY','REG_CITY_NOT_WORK_CITY','FLAG_DOCUMENT_2',
                                  'FLAG_DOCUMENT_3','FLAG_DOCUMENT_4','FLAG_DOCUMENT_5','FLAG_DOCUMENT_6',
                                  'FLAG_DOCUMENT_7','FLAG_DOCUMENT_8','FLAG_DOCUMENT_9',
                                  'FLAG_DOCUMENT_10','FLAG_DOCUMENT_11','FLAG_DOCUMENT_12','FLAG_DOCUMENT_13',
                                  'FLAG_DOCUMENT_14','FLAG_DOCUMENT_15','FLAG_DOCUMENT_16','FLAG_DOCUMENT_17',
                                  'FLAG_DOCUMENT_18','FLAG_DOCUMENT_19','FLAG_DOCUMENT_20','FLAG_DOCUMENT_21',
                                  'NFLAG_INSURED_ON_APPROVAL','NAME_CONTRACT_TYPE_x','CODE_GENDER',
                                  'NAME_TYPE_SUITE_x','NAME_INCOME_TYPE','NAME_EDUCATION_TYPE','NAME_FAMILY_STATUS',
                                  'NAME_HOUSING_TYPE','WEEKDAY_APPR_PROCESS_START_x','ORGANIZATION_TYPE','NAME_CONTRACT_TYPE_y',
                                  'WEEKDAY_APPR_PROCESS_START_y','NAME_CASH_LOAN_PURPOSE','NAME_CONTRACT_STATUS','NAME_PAYMENT_TYPE',
                                  'CODE_REJECT_REASON','NAME_TYPE_SUITE_y','NAME_CLIENT_TYPE','NAME_GOODS_CATEGORY',
                                  'NAME_PORTFOLIO','NAME_PRODUCT_TYPE','CHANNEL_TYPE','NAME_SELLER_INDUSTRY',
                                  'NAME_YIELD_GROUP','PRODUCT_COMBINATION']], drop_first=True)
dummy1.head()


# Adding the results to the master dataframe
mergeddf = pd.concat([mergeddf, dummy1], axis=1)
mergeddf.head()


mergeddf = mergeddf.drop(['FLAG_OWN_CAR','FLAG_OWN_REALTY','FLAG_MOBIL',
                          'FLAG_EMP_PHONE','FLAG_WORK_PHONE','FLAG_CONT_MOBILE',
                          'FLAG_PHONE','FLAG_EMAIL','REGION_RATING_CLIENT',
                          'REGION_RATING_CLIENT_W_CITY','REG_REGION_NOT_LIVE_REGION',
                          'REG_REGION_NOT_WORK_REGION','LIVE_REGION_NOT_WORK_REGION',
                          'REG_CITY_NOT_LIVE_CITY','REG_CITY_NOT_WORK_CITY','FLAG_DOCUMENT_2',
                          'FLAG_DOCUMENT_3','FLAG_DOCUMENT_4','FLAG_DOCUMENT_5','FLAG_DOCUMENT_6',
                          'FLAG_DOCUMENT_7','FLAG_DOCUMENT_8','FLAG_DOCUMENT_9',
                          'FLAG_DOCUMENT_10','FLAG_DOCUMENT_11','FLAG_DOCUMENT_12','FLAG_DOCUMENT_13',
                          'FLAG_DOCUMENT_14','FLAG_DOCUMENT_15','FLAG_DOCUMENT_16','FLAG_DOCUMENT_17',
                          'FLAG_DOCUMENT_18','FLAG_DOCUMENT_19','FLAG_DOCUMENT_20','FLAG_DOCUMENT_21',
                          'NFLAG_INSURED_ON_APPROVAL','NAME_CONTRACT_TYPE_x','CODE_GENDER',
                          'NAME_TYPE_SUITE_x','NAME_INCOME_TYPE','NAME_EDUCATION_TYPE','NAME_FAMILY_STATUS',
                          'NAME_HOUSING_TYPE','WEEKDAY_APPR_PROCESS_START_x','ORGANIZATION_TYPE','NAME_CONTRACT_TYPE_y',
                          'WEEKDAY_APPR_PROCESS_START_y','NAME_CASH_LOAN_PURPOSE','NAME_CONTRACT_STATUS','NAME_PAYMENT_TYPE',
                          'CODE_REJECT_REASON','NAME_TYPE_SUITE_y','NAME_CLIENT_TYPE','NAME_GOODS_CATEGORY',
                          'NAME_PORTFOLIO','NAME_PRODUCT_TYPE','CHANNEL_TYPE','NAME_SELLER_INDUSTRY',
                          'NAME_YIELD_GROUP','PRODUCT_COMBINATION'], axis = 1)
mergeddf.head()


mergeddf.shape

(1406625, 292)


mergeddfs=mergeddf.sample(n = 7000)


from sklearn.model_selection import train_test_split

# Putting feature variable to X
X = mergeddfs.drop(['TARGET'], axis=1)


X.head()


X.shape

(7000, 291)


y = mergeddfs['TARGET']


y.head()

620985     0
1030348    1
206555     0
1257561    0
1283370    0
Name: TARGET, dtype: int64


X_train, X_test, y_train, y_test = train_test_split(X, y, train_size=0.7, random_state=70)


X_train.head()


X_train.shape

(4900, 291)


X_test.head()


X_test.shape

(2100, 291)


y_train.head()

886912     0
1345274    0
710187     0
969891     0
1169924    0
Name: TARGET, dtype: int64


y_train.shape

(4900,)


y_test.head()

563940    0
186208    0
739774    0
767186    0
502320    0
Name: TARGET, dtype: int64


y_test.shape

(2100,)


from sklearn.preprocessing import StandardScaler

scaler = StandardScaler()

X_train[['CNT_CHILDREN','AMT_INCOME_TOTAL','AMT_CREDIT_x','AMT_ANNUITY_x',
         'AMT_GOODS_PRICE_x','REGION_POPULATION_RELATIVE','DAYS_BIRTH',
         'DAYS_EMPLOYED','DAYS_REGISTRATION','DAYS_ID_PUBLISH','CNT_FAM_MEMBERS',
         'HOUR_APPR_PROCESS_START_x','LIVE_CITY_NOT_WORK_CITY','OBS_30_CNT_SOCIAL_CIRCLE',
         'DEF_30_CNT_SOCIAL_CIRCLE','OBS_60_CNT_SOCIAL_CIRCLE','DEF_60_CNT_SOCIAL_CIRCLE',
         'DAYS_LAST_PHONE_CHANGE','AMT_REQ_CREDIT_BUREAU_HOUR','AMT_REQ_CREDIT_BUREAU_DAY',
         'AMT_REQ_CREDIT_BUREAU_WEEK','AMT_REQ_CREDIT_BUREAU_MON','AMT_REQ_CREDIT_BUREAU_QRT',
         'AMT_REQ_CREDIT_BUREAU_YEAR','AMT_ANNUITY_y','AMT_APPLICATION','AMT_CREDIT_y',
         'AMT_GOODS_PRICE_y','HOUR_APPR_PROCESS_START_y','FLAG_LAST_APPL_PER_CONTRACT',
         'NFLAG_LAST_APPL_IN_DAY','DAYS_DECISION','SELLERPLACE_AREA','CNT_PAYMENT',
         'DAYS_FIRST_DRAWING','DAYS_FIRST_DUE','DAYS_LAST_DUE_1ST_VERSION','DAYS_LAST_DUE',
         'DAYS_TERMINATION']] = scaler.fit_transform(X_train[['CNT_CHILDREN','AMT_INCOME_TOTAL','AMT_CREDIT_x',
                                                               'AMT_ANNUITY_x','AMT_GOODS_PRICE_x','REGION_POPULATION_RELATIVE',
                                                               'DAYS_BIRTH','DAYS_EMPLOYED','DAYS_REGISTRATION','DAYS_ID_PUBLISH',
                                                               'CNT_FAM_MEMBERS','HOUR_APPR_PROCESS_START_x','LIVE_CITY_NOT_WORK_CITY',
                                                               'OBS_30_CNT_SOCIAL_CIRCLE','DEF_30_CNT_SOCIAL_CIRCLE','OBS_60_CNT_SOCIAL_CIRCLE',
                                                               'DEF_60_CNT_SOCIAL_CIRCLE','DAYS_LAST_PHONE_CHANGE','AMT_REQ_CREDIT_BUREAU_HOUR',
                                                               'AMT_REQ_CREDIT_BUREAU_DAY','AMT_REQ_CREDIT_BUREAU_WEEK','AMT_REQ_CREDIT_BUREAU_MON',
                                                               'AMT_REQ_CREDIT_BUREAU_QRT','AMT_REQ_CREDIT_BUREAU_YEAR','AMT_ANNUITY_y','AMT_APPLICATION',
                                                               'AMT_CREDIT_y','AMT_GOODS_PRICE_y','HOUR_APPR_PROCESS_START_y','FLAG_LAST_APPL_PER_CONTRACT',
                                                               'NFLAG_LAST_APPL_IN_DAY','DAYS_DECISION','SELLERPLACE_AREA','CNT_PAYMENT','DAYS_FIRST_DRAWING',
                                                               'DAYS_FIRST_DUE','DAYS_LAST_DUE_1ST_VERSION','DAYS_LAST_DUE','DAYS_TERMINATION']])

X_train.head()


X_test[['CNT_CHILDREN','AMT_INCOME_TOTAL','AMT_CREDIT_x','AMT_ANNUITY_x',
         'AMT_GOODS_PRICE_x','REGION_POPULATION_RELATIVE','DAYS_BIRTH',
         'DAYS_EMPLOYED','DAYS_REGISTRATION','DAYS_ID_PUBLISH','CNT_FAM_MEMBERS',
         'HOUR_APPR_PROCESS_START_x','LIVE_CITY_NOT_WORK_CITY','OBS_30_CNT_SOCIAL_CIRCLE',
         'DEF_30_CNT_SOCIAL_CIRCLE','OBS_60_CNT_SOCIAL_CIRCLE','DEF_60_CNT_SOCIAL_CIRCLE',
         'DAYS_LAST_PHONE_CHANGE','AMT_REQ_CREDIT_BUREAU_HOUR','AMT_REQ_CREDIT_BUREAU_DAY',
         'AMT_REQ_CREDIT_BUREAU_WEEK','AMT_REQ_CREDIT_BUREAU_MON','AMT_REQ_CREDIT_BUREAU_QRT',
         'AMT_REQ_CREDIT_BUREAU_YEAR','AMT_ANNUITY_y','AMT_APPLICATION','AMT_CREDIT_y',
         'AMT_GOODS_PRICE_y','HOUR_APPR_PROCESS_START_y','FLAG_LAST_APPL_PER_CONTRACT',
         'NFLAG_LAST_APPL_IN_DAY','DAYS_DECISION','SELLERPLACE_AREA','CNT_PAYMENT',
         'DAYS_FIRST_DRAWING','DAYS_FIRST_DUE','DAYS_LAST_DUE_1ST_VERSION','DAYS_LAST_DUE',
         'DAYS_TERMINATION']] = scaler.transform(X_test[['CNT_CHILDREN','AMT_INCOME_TOTAL','AMT_CREDIT_x',
                                                               'AMT_ANNUITY_x','AMT_GOODS_PRICE_x','REGION_POPULATION_RELATIVE',
                                                               'DAYS_BIRTH','DAYS_EMPLOYED','DAYS_REGISTRATION','DAYS_ID_PUBLISH',
                                                               'CNT_FAM_MEMBERS','HOUR_APPR_PROCESS_START_x','LIVE_CITY_NOT_WORK_CITY',
                                                               'OBS_30_CNT_SOCIAL_CIRCLE','DEF_30_CNT_SOCIAL_CIRCLE','OBS_60_CNT_SOCIAL_CIRCLE',
                                                               'DEF_60_CNT_SOCIAL_CIRCLE','DAYS_LAST_PHONE_CHANGE','AMT_REQ_CREDIT_BUREAU_HOUR',
                                                               'AMT_REQ_CREDIT_BUREAU_DAY','AMT_REQ_CREDIT_BUREAU_WEEK','AMT_REQ_CREDIT_BUREAU_MON',
                                                               'AMT_REQ_CREDIT_BUREAU_QRT','AMT_REQ_CREDIT_BUREAU_YEAR','AMT_ANNUITY_y','AMT_APPLICATION',
                                                               'AMT_CREDIT_y','AMT_GOODS_PRICE_y','HOUR_APPR_PROCESS_START_y','FLAG_LAST_APPL_PER_CONTRACT',
                                                               'NFLAG_LAST_APPL_IN_DAY','DAYS_DECISION','SELLERPLACE_AREA','CNT_PAYMENT','DAYS_FIRST_DRAWING',
                                                               'DAYS_FIRST_DUE','DAYS_LAST_DUE_1ST_VERSION','DAYS_LAST_DUE','DAYS_TERMINATION']])

X_test.head()


X_test[['CNT_CHILDREN','AMT_INCOME_TOTAL','AMT_CREDIT_x','AMT_ANNUITY_x',
         'AMT_GOODS_PRICE_x','REGION_POPULATION_RELATIVE','DAYS_BIRTH',
         'DAYS_EMPLOYED','DAYS_REGISTRATION','DAYS_ID_PUBLISH','CNT_FAM_MEMBERS',
         'HOUR_APPR_PROCESS_START_x','LIVE_CITY_NOT_WORK_CITY','OBS_30_CNT_SOCIAL_CIRCLE',
         'DEF_30_CNT_SOCIAL_CIRCLE','OBS_60_CNT_SOCIAL_CIRCLE','DEF_60_CNT_SOCIAL_CIRCLE',
         'DAYS_LAST_PHONE_CHANGE','AMT_REQ_CREDIT_BUREAU_HOUR','AMT_REQ_CREDIT_BUREAU_DAY',
         'AMT_REQ_CREDIT_BUREAU_WEEK','AMT_REQ_CREDIT_BUREAU_MON','AMT_REQ_CREDIT_BUREAU_QRT',
         'AMT_REQ_CREDIT_BUREAU_YEAR','AMT_ANNUITY_y','AMT_APPLICATION','AMT_CREDIT_y',
         'AMT_GOODS_PRICE_y','HOUR_APPR_PROCESS_START_y','FLAG_LAST_APPL_PER_CONTRACT',
         'NFLAG_LAST_APPL_IN_DAY','DAYS_DECISION','SELLERPLACE_AREA','CNT_PAYMENT',
         'DAYS_FIRST_DRAWING','DAYS_FIRST_DUE','DAYS_LAST_DUE_1ST_VERSION','DAYS_LAST_DUE',
         'DAYS_TERMINATION']] = scaler.transform(X_test[['CNT_CHILDREN','AMT_INCOME_TOTAL','AMT_CREDIT_x',
                                                               'AMT_ANNUITY_x','AMT_GOODS_PRICE_x','REGION_POPULATION_RELATIVE',
                                                               'DAYS_BIRTH','DAYS_EMPLOYED','DAYS_REGISTRATION','DAYS_ID_PUBLISH',
                                                               'CNT_FAM_MEMBERS','HOUR_APPR_PROCESS_START_x','LIVE_CITY_NOT_WORK_CITY',
                                                               'OBS_30_CNT_SOCIAL_CIRCLE','DEF_30_CNT_SOCIAL_CIRCLE','OBS_60_CNT_SOCIAL_CIRCLE',
                                                               'DEF_60_CNT_SOCIAL_CIRCLE','DAYS_LAST_PHONE_CHANGE','AMT_REQ_CREDIT_BUREAU_HOUR',
                                                               'AMT_REQ_CREDIT_BUREAU_DAY','AMT_REQ_CREDIT_BUREAU_WEEK','AMT_REQ_CREDIT_BUREAU_MON',
                                                               'AMT_REQ_CREDIT_BUREAU_QRT','AMT_REQ_CREDIT_BUREAU_YEAR','AMT_ANNUITY_y','AMT_APPLICATION',
                                                               'AMT_CREDIT_y','AMT_GOODS_PRICE_y','HOUR_APPR_PROCESS_START_y','FLAG_LAST_APPL_PER_CONTRACT',
                                                               'NFLAG_LAST_APPL_IN_DAY','DAYS_DECISION','SELLERPLACE_AREA','CNT_PAYMENT','DAYS_FIRST_DRAWING',
                                                               'DAYS_FIRST_DUE','DAYS_LAST_DUE_1ST_VERSION','DAYS_LAST_DUE','DAYS_TERMINATION']])

X_test.head()


Target = round((sum(mergeddf['TARGET'])/len(mergeddf['TARGET'].index))*100,2)
print("We have almost {} %  Converted rate after successful data manipulation".format(Target))

We have almost 8.66 %  Converted rate after successful data manipulation


from sklearn.neighbors import KNeighborsClassifier
from sklearn.metrics import accuracy_score
model = KNeighborsClassifier()


model.fit(X_train,y_train)

KNeighborsClassifier()


predict_train = model.predict(X_train)
predict_train

array([0, 0, 0, ..., 0, 0, 0], dtype=int64)


trainaccuracy = accuracy_score(y_train,predict_train)
print('accuracy_score on train dataset : ', trainaccuracy)

accuracy_score on train dataset :  0.9061224489795918


X_train.shape

(4900, 291)


X_test.shape

(2100, 291)


model.fit(X_train,y_train)

KNeighborsClassifier()


predict_train = model.predict(X_train)
predict_train

array([0, 0, 0, ..., 0, 0, 0], dtype=int64)


trainaccuracy = accuracy_score(y_train,predict_train)
print('accuracy_score on train dataset : ', trainaccuracy)

accuracy_score on train dataset :  0.9061224489795918


from sklearn import metrics
# Confusion matrix 
confusion = metrics.confusion_matrix(y_train, predict_train )
print(confusion)

[[4411   20]
 [ 440   29]]


TP = confusion[1,1] # true positive 
TN = confusion[0,0] # true negatives
FP = confusion[0,1] # false positives
FN = confusion[1,0] # false negatives


# Let's see the sensitivity of our model
trainsensitivity= TP / float(TP+FN)
trainsensitivity

0.06183368869936034


# Let us calculate specificity
trainspecificity= TN / float(TN+FP)
trainspecificity

0.9954863461972466


# Calculate false postive rate - predicting Defaulted when customer does not have Defaulted
print(FP/ float(TN+FP))

0.0045136538027533285


# Positive predictive value 
print (TP / float(TP+FP))

0.5918367346938775


print(TN / float(TN+ FN))

0.909297052154195


def draw_roc( actual, probs ):
    fpr, tpr, thresholds = metrics.roc_curve( actual, probs,
                                              drop_intermediate = False )
    auc_score = metrics.roc_auc_score( actual, probs )
    plt.figure(figsize=(5, 5))
    plt.plot( fpr, tpr, label='ROC curve (area = %0.2f)' % auc_score )
    plt.plot([0, 1], [0, 1], 'k--')
    plt.xlim([0.0, 1.0])
    plt.ylim([0.0, 1.05])
    plt.xlabel('False Positive Rate or [1 - True Negative Rate]')
    plt.ylabel('True Positive Rate')
    plt.title('Receiver operating characteristic example')
    plt.legend(loc="lower right")
    plt.show()

    return None


draw_roc(y_train,predict_train)


from sklearn.metrics import precision_score, recall_score
precision_score(y_train,predict_train)

0.5918367346938775


recall_score(y_train,predict_train)

0.06183368869936034


# predict the target on the test dataset
predict_test = model.predict(X_test)
print('Target on test data\n\n',predict_test)

Target on test data

 [0 0 0 ... 0 0 0]


confusion2 = metrics.confusion_matrix(y_test, predict_test )
print(confusion2)

[[1928    0]
 [ 172    0]]


TP = confusion2[1,1] # true positive 
TN = confusion2[0,0] # true negatives
FP = confusion2[0,1] # false positives
FN = confusion2[1,0] # false negatives


# Let's check the overall accuracy.
testaccuracy= accuracy_score(y_test,predict_test)
testaccuracy

0.9180952380952381


# Let's see the sensitivity of our lmodel
testsensitivity=TP / float(TP+FN)
testsensitivity

0.0


# Let us calculate specificity
testspecificity= TN / float(TN+FP)
testspecificity

1.0


# Let us compare the values obtained for Train & Test:
print("Train Data Accuracy    :{} %".format(round((trainaccuracy*100),2)))
print("Train Data Sensitivity :{} %".format(round((trainsensitivity*100),2)))
print("Train Data Specificity :{} %".format(round((trainspecificity*100),2)))
print("Test Data Accuracy     :{} %".format(round((testaccuracy*100),2)))
print("Test Data Sensitivity  :{} %".format(round((testsensitivity*100),2)))
print("Test Data Specificity  :{} %".format(round((testspecificity*100),2)))

Train Data Accuracy    :90.61 %
Train Data Sensitivity :6.18 %
Train Data Specificity :99.55 %
Test Data Accuracy     :91.81 %
Test Data Sensitivity  :0.0 %
Test Data Specificity  :100.0 %

	SK_ID_CURR	TARGET	NAME_CONTRACT_TYPE	CODE_GENDER	FLAG_OWN_CAR	FLAG_OWN_REALTY	AMT_INCOME_TOTAL	AMT_CREDIT	AMT_ANNUITY	AMT_GOODS_PRICE	NAME_TYPE_SUITE	NAME_INCOME_TYPE	NAME_EDUCATION_TYPE	NAME_FAMILY_STATUS	NAME_HOUSING_TYPE	REGION_POPULATION_RELATIVE	DAYS_BIRTH	DAYS_EMPLOYED	DAYS_REGISTRATION	DAYS_ID_PUBLISH	OWN_CAR_AGE	FLAG_MOBIL	FLAG_EMP_PHONE	FLAG_WORK_PHONE	FLAG_CONT_MOBILE	FLAG_PHONE	OCCUPATION_TYPE	CNT_FAM_MEMBERS	REGION_RATING_CLIENT	REGION_RATING_CLIENT_W_CITY	WEEKDAY_APPR_PROCESS_START	HOUR_APPR_PROCESS_START	ORGANIZATION_TYPE	EXT_SOURCE_1	EXT_SOURCE_2	EXT_SOURCE_3	APARTMENTS_AVG	BASEMENTAREA_AVG	YEARS_BEGINEXPLUATATION_AVG	YEARS_BUILD_AVG	COMMONAREA_AVG	ELEVATORS_AVG	ENTRANCES_AVG	FLOORSMAX_AVG	FLOORSMIN_AVG	LANDAREA_AVG	LIVINGAPARTMENTS_AVG	LIVINGAREA_AVG	NONLIVINGAPARTMENTS_AVG	NONLIVINGAREA_AVG	APARTMENTS_MODE	BASEMENTAREA_MODE	YEARS_BEGINEXPLUATATION_MODE	YEARS_BUILD_MODE	COMMONAREA_MODE	ELEVATORS_MODE	ENTRANCES_MODE	FLOORSMAX_MODE	FLOORSMIN_MODE	LANDAREA_MODE	LIVINGAPARTMENTS_MODE	LIVINGAREA_MODE	NONLIVINGAPARTMENTS_MODE	NONLIVINGAREA_MODE	APARTMENTS_MEDI	BASEMENTAREA_MEDI	YEARS_BEGINEXPLUATATION_MEDI	YEARS_BUILD_MEDI	COMMONAREA_MEDI	ELEVATORS_MEDI	ENTRANCES_MEDI	FLOORSMAX_MEDI	FLOORSMIN_MEDI	LANDAREA_MEDI	LIVINGAPARTMENTS_MEDI	LIVINGAREA_MEDI	NONLIVINGAPARTMENTS_MEDI	NONLIVINGAREA_MEDI	FONDKAPREMONT_MODE	HOUSETYPE_MODE	TOTALAREA_MODE	WALLSMATERIAL_MODE	EMERGENCYSTATE_MODE	OBS_30_CNT_SOCIAL_CIRCLE	DEF_30_CNT_SOCIAL_CIRCLE	OBS_60_CNT_SOCIAL_CIRCLE	DEF_60_CNT_SOCIAL_CIRCLE	DAYS_LAST_PHONE_CHANGE	FLAG_DOCUMENT_3	AMT_REQ_CREDIT_BUREAU_YEAR
0	100002	1	Cash loans	M	N	Y	202500.0	406597.5	24700.5	351000.0	Unaccompanied	Working	Secondary / secondary special	Single / not married	House / apartment	0.018801	-9461	-637	-3648.0	-2120	NaN	1	1	0	1	1	Laborers	1.0	2	2	WEDNESDAY	10	Business Entity Type 3	0.083037	0.262949	0.139376	0.0247	0.0369	0.9722	0.6192	0.0143	0.00	0.0690	0.0833	0.1250	0.0369	0.0202	0.0190	0.0000	0.0000	0.0252	0.0383	0.9722	0.6341	0.0144	0.0000	0.0690	0.0833	0.1250	0.0377	0.022	0.0198	0.0	0.0	0.0250	0.0369	0.9722	0.6243	0.0144	0.00	0.0690	0.0833	0.1250	0.0375	0.0205	0.0193	0.0000	0.00	reg oper account	block of flats	0.0149	Stone, brick	No	2.0	2.0	2.0	2.0	-1134.0	1	1.0
1	100003	0	Cash loans	F	N	N	270000.0	1293502.5	35698.5	1129500.0	Family	State servant	Higher education	Married	House / apartment	0.003541	-16765	-1188	-1186.0	-291	NaN	1	1	0	1	1	Core staff	2.0	1	1	MONDAY	11	School	0.311267	0.622246	NaN	0.0959	0.0529	0.9851	0.7960	0.0605	0.08	0.0345	0.2917	0.3333	0.0130	0.0773	0.0549	0.0039	0.0098	0.0924	0.0538	0.9851	0.8040	0.0497	0.0806	0.0345	0.2917	0.3333	0.0128	0.079	0.0554	0.0	0.0	0.0968	0.0529	0.9851	0.7987	0.0608	0.08	0.0345	0.2917	0.3333	0.0132	0.0787	0.0558	0.0039	0.01	reg oper account	block of flats	0.0714	Block	No	1.0	0.0	1.0	0.0	-828.0	1	0.0
2	100004	0	Revolving loans	M	Y	Y	67500.0	135000.0	6750.0	135000.0	Unaccompanied	Working	Secondary / secondary special	Single / not married	House / apartment	0.010032	-19046	-225	-4260.0	-2531	26.0	1	1	1	1	1	Laborers	1.0	2	2	MONDAY	9	Government	NaN	0.555912	0.729567	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	0.0	0.0	0.0	0.0	-815.0	0	0.0

	TARGET	count
SK_ID_CURR
100002	1	1
100003	0	3
100004	0	1
100006	0	9
100007	0	6
100008	0	5
100009	0	7
100010	0	1
100011	0	4
100012	0	4

	TARGET	count
SK_ID_CURR
100002	1	1
333349	1	1
333587	1	1
333582	1	1
333534	1	1
333506	1	1
333419	1	1
333355	1	1
333337	1	1
334761	1	1

	FLAG_OWN_CAR_1	FLAG_OWN_REALTY_1	FLAG_EMP_PHONE_1	FLAG_WORK_PHONE_1	FLAG_CONT_MOBILE_1	FLAG_PHONE_1	REGION_RATING_CLIENT_2	REGION_RATING_CLIENT_W_CITY_2	FLAG_DOCUMENT_3_1	NFLAG_INSURED_ON_APPROVAL_1.0	NAME_CONTRACT_TYPE_x_Revolving loans	CODE_GENDER_M	NAME_TYPE_SUITE_x_Family	NAME_TYPE_SUITE_x_Unaccompanied	NAME_INCOME_TYPE_State servant	NAME_INCOME_TYPE_Working	NAME_EDUCATION_TYPE_Higher education	NAME_EDUCATION_TYPE_Secondary / secondary special	NAME_FAMILY_STATUS_Married	NAME_FAMILY_STATUS_Single / not married	NAME_HOUSING_TYPE_House / apartment	WEEKDAY_APPR_PROCESS_START_x_MONDAY	WEEKDAY_APPR_PROCESS_START_x_WEDNESDAY	ORGANIZATION_TYPE_Business Entity Type 3	ORGANIZATION_TYPE_Government	ORGANIZATION_TYPE_School	NAME_CONTRACT_TYPE_y_Consumer loans	WEEKDAY_APPR_PROCESS_START_y_SATURDAY	WEEKDAY_APPR_PROCESS_START_y_SUNDAY	NAME_CASH_LOAN_PURPOSE_XAP	NAME_CASH_LOAN_PURPOSE_XNA	NAME_PAYMENT_TYPE_XNA	CODE_REJECT_REASON_XAP	NAME_TYPE_SUITE_y_Family	NAME_TYPE_SUITE_y_Unaccompanied	NAME_CLIENT_TYPE_Refreshed	NAME_CLIENT_TYPE_Repeater	NAME_GOODS_CATEGORY_Consumer Electronics	NAME_GOODS_CATEGORY_Furniture	NAME_GOODS_CATEGORY_Mobile	NAME_GOODS_CATEGORY_Vehicles	NAME_GOODS_CATEGORY_XNA	NAME_PORTFOLIO_Cash	NAME_PORTFOLIO_POS	NAME_PRODUCT_TYPE_x-sell	CHANNEL_TYPE_Country-wide	CHANNEL_TYPE_Credit and cash offices	CHANNEL_TYPE_Regional / Local	CHANNEL_TYPE_Stone	NAME_SELLER_INDUSTRY_Connectivity	NAME_SELLER_INDUSTRY_Consumer electronics	NAME_SELLER_INDUSTRY_Furniture	NAME_SELLER_INDUSTRY_XNA	NAME_YIELD_GROUP_low_normal	NAME_YIELD_GROUP_middle	PRODUCT_COMBINATION_Cash X-Sell: low	PRODUCT_COMBINATION_POS household with interest	PRODUCT_COMBINATION_POS industry with interest	PRODUCT_COMBINATION_POS mobile without interest	PRODUCT_COMBINATION_POS other with interest
0	0	1	1	0	1	1	1	1	1	0	0	1	0	1	0	1	0	1	0	1	1	0	1	1	0	0	1	1	0	1	0	1	1	0	1	0	0	0	0	0	1	0	0	1	0	0	0	0	1	0	0	0	0	1	0	0	0	0	0	1
1	0	0	1	0	1	1	0	0	1	1	0	0	1	0	1	0	1	0	1	0	1	1	0	0	0	1	0	0	0	0	1	1	1	0	1	0	1	0	0	0	0	1	1	0	1	0	1	0	0	0	0	0	1	1	0	1	0	0	0	0
2	0	0	1	0	1	1	0	0	1	0	0	0	1	0	1	0	1	0	1	0	1	1	0	0	0	1	1	0	1	1	0	0	1	1	0	1	0	0	1	0	0	0	0	1	0	0	0	0	1	0	0	1	0	0	1	0	0	1	0	0
3	0	0	1	0	1	1	0	0	1	1	0	0	1	0	1	0	1	0	1	0	1	1	0	0	0	1	1	1	0	1	0	0	1	1	0	1	0	1	0	0	0	0	0	1	0	1	0	0	0	0	1	0	0	0	1	0	1	0	0	0
4	1	1	1	1	1	1	1	1	0	0	1	1	0	1	0	1	0	1	0	1	1	1	0	0	1	0	1	0	0	1	0	0	1	0	1	0	0	0	0	1	0	0	0	1	0	0	0	1	0	1	0	0	0	0	1	0	0	0	1	0

	TARGET	NAME_CONTRACT_TYPE_x	CODE_GENDER	FLAG_OWN_CAR	FLAG_OWN_REALTY	AMT_INCOME_TOTAL	AMT_CREDIT_x	AMT_ANNUITY_x	AMT_GOODS_PRICE_x	NAME_TYPE_SUITE_x	NAME_INCOME_TYPE	NAME_EDUCATION_TYPE	NAME_FAMILY_STATUS	NAME_HOUSING_TYPE	REGION_POPULATION_RELATIVE	DAYS_BIRTH	DAYS_EMPLOYED	DAYS_REGISTRATION	DAYS_ID_PUBLISH	FLAG_MOBIL	FLAG_EMP_PHONE	FLAG_WORK_PHONE	FLAG_CONT_MOBILE	FLAG_PHONE	CNT_FAM_MEMBERS	REGION_RATING_CLIENT	REGION_RATING_CLIENT_W_CITY	WEEKDAY_APPR_PROCESS_START_x	HOUR_APPR_PROCESS_START_x	ORGANIZATION_TYPE	OBS_30_CNT_SOCIAL_CIRCLE	DEF_30_CNT_SOCIAL_CIRCLE	OBS_60_CNT_SOCIAL_CIRCLE	DEF_60_CNT_SOCIAL_CIRCLE	DAYS_LAST_PHONE_CHANGE	FLAG_DOCUMENT_3	AMT_REQ_CREDIT_BUREAU_YEAR	NAME_CONTRACT_TYPE_y	AMT_ANNUITY_y	AMT_APPLICATION	AMT_CREDIT_y	AMT_GOODS_PRICE_y	WEEKDAY_APPR_PROCESS_START_y	HOUR_APPR_PROCESS_START_y	FLAG_LAST_APPL_PER_CONTRACT	NFLAG_LAST_APPL_IN_DAY	NAME_CASH_LOAN_PURPOSE	NAME_CONTRACT_STATUS	DAYS_DECISION	NAME_PAYMENT_TYPE	CODE_REJECT_REASON	NAME_TYPE_SUITE_y	NAME_CLIENT_TYPE	NAME_GOODS_CATEGORY	NAME_PORTFOLIO	NAME_PRODUCT_TYPE	CHANNEL_TYPE	SELLERPLACE_AREA	NAME_SELLER_INDUSTRY	CNT_PAYMENT	NAME_YIELD_GROUP	PRODUCT_COMBINATION	DAYS_FIRST_DRAWING	DAYS_FIRST_DUE	DAYS_LAST_DUE_1ST_VERSION	DAYS_LAST_DUE	DAYS_TERMINATION	NFLAG_INSURED_ON_APPROVAL	FLAG_OWN_CAR_1	FLAG_OWN_REALTY_1	FLAG_EMP_PHONE_1	FLAG_WORK_PHONE_1	FLAG_CONT_MOBILE_1	FLAG_PHONE_1	REGION_RATING_CLIENT_2	REGION_RATING_CLIENT_W_CITY_2	FLAG_DOCUMENT_3_1	NFLAG_INSURED_ON_APPROVAL_1.0	NAME_CONTRACT_TYPE_x_Revolving loans	CODE_GENDER_M	NAME_TYPE_SUITE_x_Family	NAME_TYPE_SUITE_x_Unaccompanied	NAME_INCOME_TYPE_State servant	NAME_INCOME_TYPE_Working	NAME_EDUCATION_TYPE_Higher education	NAME_EDUCATION_TYPE_Secondary / secondary special	NAME_FAMILY_STATUS_Married	NAME_FAMILY_STATUS_Single / not married	NAME_HOUSING_TYPE_House / apartment	WEEKDAY_APPR_PROCESS_START_x_MONDAY	WEEKDAY_APPR_PROCESS_START_x_WEDNESDAY	ORGANIZATION_TYPE_Business Entity Type 3	ORGANIZATION_TYPE_Government	ORGANIZATION_TYPE_School	NAME_CONTRACT_TYPE_y_Consumer loans	WEEKDAY_APPR_PROCESS_START_y_SATURDAY	WEEKDAY_APPR_PROCESS_START_y_SUNDAY	NAME_CASH_LOAN_PURPOSE_XAP	NAME_CASH_LOAN_PURPOSE_XNA	NAME_PAYMENT_TYPE_XNA	CODE_REJECT_REASON_XAP	NAME_TYPE_SUITE_y_Family	NAME_TYPE_SUITE_y_Unaccompanied	NAME_CLIENT_TYPE_Refreshed	NAME_CLIENT_TYPE_Repeater	NAME_GOODS_CATEGORY_Consumer Electronics	NAME_GOODS_CATEGORY_Furniture	NAME_GOODS_CATEGORY_Mobile	NAME_GOODS_CATEGORY_Vehicles	NAME_GOODS_CATEGORY_XNA	NAME_PORTFOLIO_Cash	NAME_PORTFOLIO_POS	NAME_PRODUCT_TYPE_x-sell	CHANNEL_TYPE_Country-wide	CHANNEL_TYPE_Credit and cash offices	CHANNEL_TYPE_Regional / Local	CHANNEL_TYPE_Stone	NAME_SELLER_INDUSTRY_Connectivity	NAME_SELLER_INDUSTRY_Consumer electronics	NAME_SELLER_INDUSTRY_Furniture	NAME_SELLER_INDUSTRY_XNA	NAME_YIELD_GROUP_low_normal	NAME_YIELD_GROUP_middle	PRODUCT_COMBINATION_Cash X-Sell: low	PRODUCT_COMBINATION_POS household with interest	PRODUCT_COMBINATION_POS industry with interest	PRODUCT_COMBINATION_POS mobile without interest	PRODUCT_COMBINATION_POS other with interest
0	1	Cash loans	M	0	1	202500.0	406597.5	24700.5	351000.0	Unaccompanied	Working	Secondary / secondary special	Single / not married	House / apartment	0.018801	9461	-637	-3648.0	2120	1	1	0	1	1	1.0	2	2	WEDNESDAY	10	Business Entity Type 3	2.0	2.0	2.0	2.0	1134.0	1	1.0	Consumer loans	9251.775	179055.0	179055.0	179055.0	SATURDAY	9	1	1	XAP	Approved	-606	XNA	XAP	Unaccompanied	New	Vehicles	POS	XNA	Stone	500	Auto technology	24.0	low_normal	POS other with interest	365243.0	-565.0	125.0	-25.0	-17.0	0.0	0	1	1	0	1	1	1	1	1	0	0	1	0	1	0	1	0	1	0	1	1	0	1	1	0	0	1	1	0	1	0	1	1	0	1	0	0	0	0	0	1	0	0	1	0	0	0	0	1	0	0	0	0	1	0	0	0	0	0	1
1	0	Cash loans	F	0	0	270000.0	1293502.5	35698.5	1129500.0	Family	State servant	Higher education	Married	House / apartment	0.003541	16765	-1188	-1186.0	291	1	1	0	1	1	2.0	1	1	MONDAY	11	School	1.0	0.0	1.0	0.0	828.0	1	0.0	Cash loans	98356.995	900000.0	1035882.0	900000.0	FRIDAY	12	1	1	XNA	Approved	-746	XNA	XAP	Unaccompanied	Repeater	XNA	Cash	x-sell	Credit and cash offices	-1	XNA	12.0	low_normal	Cash X-Sell: low	365243.0	-716.0	-386.0	-536.0	-527.0	1.0	0	0	1	0	1	1	0	0	1	1	0	0	1	0	1	0	1	0	1	0	1	1	0	0	0	1	0	0	0	0	1	1	1	0	1	0	1	0	0	0	0	1	1	0	1	0	1	0	0	0	0	0	1	1	0	1	0	0	0	0
2	0	Cash loans	F	0	0	270000.0	1293502.5	35698.5	1129500.0	Family	State servant	Higher education	Married	House / apartment	0.003541	16765	-1188	-1186.0	291	1	1	0	1	1	2.0	1	1	MONDAY	11	School	1.0	0.0	1.0	0.0	828.0	1	0.0	Consumer loans	64567.665	337500.0	348637.5	337500.0	SUNDAY	17	1	1	XAP	Approved	-828	Cash through the bank	XAP	Family	Refreshed	Furniture	POS	XNA	Stone	1400	Furniture	6.0	middle	POS industry with interest	365243.0	-797.0	-647.0	-647.0	-639.0	0.0	0	0	1	0	1	1	0	0	1	0	0	0	1	0	1	0	1	0	1	0	1	1	0	0	0	1	1	0	1	1	0	0	1	1	0	1	0	0	1	0	0	0	0	1	0	0	0	0	1	0	0	1	0	0	1	0	0	1	0	0
3	0	Cash loans	F	0	0	270000.0	1293502.5	35698.5	1129500.0	Family	State servant	Higher education	Married	House / apartment	0.003541	16765	-1188	-1186.0	291	1	1	0	1	1	2.0	1	1	MONDAY	11	School	1.0	0.0	1.0	0.0	828.0	1	0.0	Consumer loans	6737.310	68809.5	68053.5	68809.5	SATURDAY	15	1	1	XAP	Approved	-2341	Cash through the bank	XAP	Family	Refreshed	Consumer Electronics	POS	XNA	Country-wide	200	Consumer electronics	12.0	middle	POS household with interest	365243.0	-2310.0	-1980.0	-1980.0	-1976.0	1.0	0	0	1	0	1	1	0	0	1	1	0	0	1	0	1	0	1	0	1	0	1	1	0	0	0	1	1	1	0	1	0	0	1	1	0	1	0	1	0	0	0	0	0	1	0	1	0	0	0	0	1	0	0	0	1	0	1	0	0	0
4	0	Revolving loans	M	1	1	67500.0	135000.0	6750.0	135000.0	Unaccompanied	Working	Secondary / secondary special	Single / not married	House / apartment	0.010032	19046	-225	-4260.0	2531	1	1	1	1	1	1.0	2	2	MONDAY	9	Government	0.0	0.0	0.0	0.0	815.0	0	0.0	Consumer loans	5357.250	24282.0	20106.0	24282.0	FRIDAY	5	1	1	XAP	Approved	-815	Cash through the bank	XAP	Unaccompanied	New	Mobile	POS	XNA	Regional / Local	30	Connectivity	4.0	middle	POS mobile without interest	365243.0	-784.0	-694.0	-724.0	-714.0	0.0	1	1	1	1	1	1	1	1	0	0	1	1	0	1	0	1	0	1	0	1	1	1	0	0	1	0	1	0	0	1	0	0	1	0	1	0	0	0	0	1	0	0	0	1	0	0	0	1	0	1	0	0	0	0	1	0	0	0	1	0

	SK_ID_PREV	SK_ID_CURR	NAME_CONTRACT_TYPE	AMT_ANNUITY	AMT_APPLICATION	AMT_CREDIT	AMT_DOWN_PAYMENT	AMT_GOODS_PRICE	WEEKDAY_APPR_PROCESS_START	HOUR_APPR_PROCESS_START	FLAG_LAST_APPL_PER_CONTRACT	NFLAG_LAST_APPL_IN_DAY	RATE_DOWN_PAYMENT	RATE_INTEREST_PRIMARY	RATE_INTEREST_PRIVILEGED	NAME_CASH_LOAN_PURPOSE	NAME_CONTRACT_STATUS	DAYS_DECISION	NAME_PAYMENT_TYPE	CODE_REJECT_REASON	NAME_TYPE_SUITE	NAME_CLIENT_TYPE	NAME_GOODS_CATEGORY	NAME_PORTFOLIO	NAME_PRODUCT_TYPE	CHANNEL_TYPE	SELLERPLACE_AREA	NAME_SELLER_INDUSTRY	CNT_PAYMENT	NAME_YIELD_GROUP	PRODUCT_COMBINATION	DAYS_FIRST_DRAWING	DAYS_FIRST_DUE	DAYS_LAST_DUE_1ST_VERSION	DAYS_LAST_DUE	DAYS_TERMINATION	NFLAG_INSURED_ON_APPROVAL
0	2030495	271877	Consumer loans	1730.430	17145.0	17145.0	0.0	17145.0	SATURDAY	15	Y	1	0.0	0.182832	0.867336	XAP	Approved	-73	Cash through the bank	XAP	NaN	Repeater	Mobile	POS	XNA	Country-wide	35	Connectivity	12.0	middle	POS mobile with interest	365243.0	-42.0	300.0	-42.0	-37.0	0.0
1	2802425	108129	Cash loans	25188.615	607500.0	679671.0	NaN	607500.0	THURSDAY	11	Y	1	NaN	NaN	NaN	XNA	Approved	-164	XNA	XAP	Unaccompanied	Repeater	XNA	Cash	x-sell	Contact center	-1	XNA	36.0	low_action	Cash X-Sell: low	365243.0	-134.0	916.0	365243.0	365243.0	1.0
2	2523466	122040	Cash loans	15060.735	112500.0	136444.5	NaN	112500.0	TUESDAY	11	Y	1	NaN	NaN	NaN	XNA	Approved	-301	Cash through the bank	XAP	Spouse, partner	Repeater	XNA	Cash	x-sell	Credit and cash offices	-1	XNA	12.0	high	Cash X-Sell: high	365243.0	-271.0	59.0	365243.0	365243.0	1.0

	Var1	Var2	Correlation
88	AMT_GOODS_PRICE	AMT_APPLICATION	1.00
89	AMT_GOODS_PRICE	AMT_CREDIT	0.99
71	AMT_CREDIT	AMT_APPLICATION	0.98
269	DAYS_TERMINATION	DAYS_LAST_DUE	0.93
87	AMT_GOODS_PRICE	AMT_ANNUITY	0.82
70	AMT_CREDIT	AMT_ANNUITY	0.82
53	AMT_APPLICATION	AMT_ANNUITY	0.81
232	DAYS_LAST_DUE_1ST_VERSION	DAYS_FIRST_DRAWING	0.80
173	CNT_PAYMENT	AMT_APPLICATION	0.68
174	CNT_PAYMENT	AMT_CREDIT	0.67

	Var1	Var2	Correlation
1798	OBS_60_CNT_SOCIAL_CIRCLE	OBS_30_CNT_SOCIAL_CIRCLE	1.00
776	FLAG_EMP_PHONE	DAYS_EMPLOYED	1.00
358	AMT_GOODS_PRICE	AMT_CREDIT	0.98
1199	REGION_RATING_CLIENT_W_CITY	REGION_RATING_CLIENT	0.96
1064	CNT_FAM_MEMBERS	CNT_CHILDREN	0.89
1858	DEF_60_CNT_SOCIAL_CIRCLE	DEF_30_CNT_SOCIAL_CIRCLE	0.87
1439	LIVE_REGION_NOT_WORK_REGION	REG_REGION_NOT_WORK_REGION	0.85
1619	LIVE_CITY_NOT_WORK_CITY	REG_CITY_NOT_WORK_CITY	0.78
299	AMT_ANNUITY	AMT_CREDIT	0.75
359	AMT_GOODS_PRICE	AMT_ANNUITY	0.75

	TARGET	count
SK_ID_CURR
265681	0	73
173680	0	72
242412	0	68
206783	0	67
389950	0	64
382179	0	64
198355	0	63
345161	0	62
446486	0	62
238250	0	61

	FLAG_OWN_CAR_1	FLAG_OWN_REALTY_1	FLAG_EMP_PHONE_1	FLAG_WORK_PHONE_1	FLAG_CONT_MOBILE_1	FLAG_PHONE_1	REGION_RATING_CLIENT_2	REGION_RATING_CLIENT_W_CITY_2	FLAG_DOCUMENT_3_1	NFLAG_INSURED_ON_APPROVAL_1.0	NAME_CONTRACT_TYPE_x_Revolving loans	CODE_GENDER_M	NAME_TYPE_SUITE_x_Family	NAME_TYPE_SUITE_x_Unaccompanied	NAME_INCOME_TYPE_State servant	NAME_INCOME_TYPE_Working	NAME_EDUCATION_TYPE_Higher education	NAME_EDUCATION_TYPE_Secondary / secondary special	NAME_FAMILY_STATUS_Married	NAME_FAMILY_STATUS_Single / not married	NAME_HOUSING_TYPE_House / apartment	WEEKDAY_APPR_PROCESS_START_x_MONDAY	WEEKDAY_APPR_PROCESS_START_x_WEDNESDAY	ORGANIZATION_TYPE_Business Entity Type 3	ORGANIZATION_TYPE_Government	ORGANIZATION_TYPE_School	NAME_CONTRACT_TYPE_y_Consumer loans	WEEKDAY_APPR_PROCESS_START_y_SATURDAY	WEEKDAY_APPR_PROCESS_START_y_SUNDAY	NAME_CASH_LOAN_PURPOSE_XAP	NAME_CASH_LOAN_PURPOSE_XNA	NAME_PAYMENT_TYPE_XNA	CODE_REJECT_REASON_XAP	NAME_TYPE_SUITE_y_Family	NAME_TYPE_SUITE_y_Unaccompanied	NAME_CLIENT_TYPE_Refreshed	NAME_CLIENT_TYPE_Repeater	NAME_GOODS_CATEGORY_Consumer Electronics	NAME_GOODS_CATEGORY_Furniture	NAME_GOODS_CATEGORY_Mobile	NAME_GOODS_CATEGORY_Vehicles	NAME_GOODS_CATEGORY_XNA	NAME_PORTFOLIO_Cash	NAME_PORTFOLIO_POS	NAME_PRODUCT_TYPE_x-sell	CHANNEL_TYPE_Country-wide	CHANNEL_TYPE_Credit and cash offices	CHANNEL_TYPE_Regional / Local	CHANNEL_TYPE_Stone	NAME_SELLER_INDUSTRY_Connectivity	NAME_SELLER_INDUSTRY_Consumer electronics	NAME_SELLER_INDUSTRY_Furniture	NAME_SELLER_INDUSTRY_XNA	NAME_YIELD_GROUP_low_normal	NAME_YIELD_GROUP_middle	PRODUCT_COMBINATION_Cash X-Sell: low	PRODUCT_COMBINATION_POS household with interest	PRODUCT_COMBINATION_POS industry with interest	PRODUCT_COMBINATION_POS mobile without interest	PRODUCT_COMBINATION_POS other with interest
0	0	1	1	0	1	1	1	1	1	0	0	1	0	1	0	1	0	1	0	1	1	0	1	1	0	0	1	1	0	1	0	1	1	0	1	0	0	0	0	0	1	0	0	1	0	0	0	0	1	0	0	0	0	1	0	0	0	0	0	1
1	0	0	1	0	1	1	0	0	1	1	0	0	1	0	1	0	1	0	1	0	1	1	0	0	0	1	0	0	0	0	1	1	1	0	1	0	1	0	0	0	0	1	1	0	1	0	1	0	0	0	0	0	1	1	0	1	0	0	0	0
2	0	0	1	0	1	1	0	0	1	0	0	0	1	0	1	0	1	0	1	0	1	1	0	0	0	1	1	0	1	1	0	0	1	1	0	1	0	0	1	0	0	0	0	1	0	0	0	0	1	0	0	1	0	0	1	0	0	1	0	0
3	0	0	1	0	1	1	0	0	1	1	0	0	1	0	1	0	1	0	1	0	1	1	0	0	0	1	1	1	0	1	0	0	1	1	0	1	0	1	0	0	0	0	0	1	0	1	0	0	0	0	1	0	0	0	1	0	1	0	0	0
4	1	1	1	1	1	1	1	1	0	0	1	1	0	1	0	1	0	1	0	1	1	1	0	0	1	0	1	0	0	1	0	0	1	0	1	0	0	0	0	1	0	0	0	1	0	0	0	1	0	1	0	0	0	0	1	0	0	0	1	0

	CNT_CHILDREN	AMT_INCOME_TOTAL	AMT_CREDIT_x	AMT_ANNUITY_x	AMT_GOODS_PRICE_x	REGION_POPULATION_RELATIVE	DAYS_BIRTH	DAYS_EMPLOYED	DAYS_REGISTRATION	DAYS_ID_PUBLISH	CNT_FAM_MEMBERS	HOUR_APPR_PROCESS_START_x	LIVE_CITY_NOT_WORK_CITY	OBS_30_CNT_SOCIAL_CIRCLE	OBS_60_CNT_SOCIAL_CIRCLE	DAYS_LAST_PHONE_CHANGE	AMT_REQ_CREDIT_BUREAU_QRT	AMT_REQ_CREDIT_BUREAU_YEAR	AMT_ANNUITY_y	AMT_APPLICATION	AMT_CREDIT_y	AMT_GOODS_PRICE_y	HOUR_APPR_PROCESS_START_y	FLAG_LAST_APPL_PER_CONTRACT	NFLAG_LAST_APPL_IN_DAY	DAYS_DECISION	SELLERPLACE_AREA	CNT_PAYMENT	DAYS_FIRST_DRAWING	DAYS_FIRST_DUE	DAYS_LAST_DUE_1ST_VERSION	DAYS_LAST_DUE	DAYS_TERMINATION	FLAG_OWN_CAR_1	FLAG_OWN_REALTY_1	FLAG_EMP_PHONE_1	FLAG_WORK_PHONE_1	FLAG_CONT_MOBILE_1	REGION_RATING_CLIENT_2	REGION_RATING_CLIENT_W_CITY_2	REG_CITY_NOT_WORK_CITY_1	FLAG_DOCUMENT_3_1	NFLAG_INSURED_ON_APPROVAL_1.0	NAME_CONTRACT_TYPE_x_Revolving loans	CODE_GENDER_M	NAME_TYPE_SUITE_x_Family	NAME_TYPE_SUITE_x_Unaccompanied	NAME_INCOME_TYPE_Working	NAME_EDUCATION_TYPE_Secondary / secondary special	NAME_FAMILY_STATUS_Married	NAME_HOUSING_TYPE_House / apartment	NAME_HOUSING_TYPE_Municipal apartment	WEEKDAY_APPR_PROCESS_START_x_SATURDAY	WEEKDAY_APPR_PROCESS_START_x_THURSDAY	WEEKDAY_APPR_PROCESS_START_x_TUESDAY	WEEKDAY_APPR_PROCESS_START_x_WEDNESDAY	ORGANIZATION_TYPE_Business Entity Type 3	ORGANIZATION_TYPE_Transport: type 2	NAME_CONTRACT_TYPE_y_Consumer loans	WEEKDAY_APPR_PROCESS_START_y_MONDAY	WEEKDAY_APPR_PROCESS_START_y_SATURDAY	WEEKDAY_APPR_PROCESS_START_y_TUESDAY	WEEKDAY_APPR_PROCESS_START_y_WEDNESDAY	NAME_CASH_LOAN_PURPOSE_Urgent needs	NAME_CASH_LOAN_PURPOSE_XAP	NAME_CASH_LOAN_PURPOSE_XNA	NAME_CONTRACT_STATUS_Canceled	NAME_PAYMENT_TYPE_XNA	CODE_REJECT_REASON_XAP	NAME_TYPE_SUITE_y_Unaccompanied	NAME_CLIENT_TYPE_Refreshed	NAME_CLIENT_TYPE_Repeater	NAME_GOODS_CATEGORY_Audio/Video	NAME_GOODS_CATEGORY_XNA	NAME_PORTFOLIO_Cash	NAME_PORTFOLIO_POS	NAME_PORTFOLIO_XNA	NAME_PRODUCT_TYPE_walk-in	CHANNEL_TYPE_Country-wide	CHANNEL_TYPE_Credit and cash offices	NAME_SELLER_INDUSTRY_Connectivity	NAME_SELLER_INDUSTRY_Consumer electronics	NAME_SELLER_INDUSTRY_XNA	NAME_YIELD_GROUP_middle	PRODUCT_COMBINATION_Cash	PRODUCT_COMBINATION_Cash Street: middle	PRODUCT_COMBINATION_POS household with interest
620985	2	87750.0	314100.0	16573.5	225000.0	0.018634	10856	-1455	-2167.0	3394	4.0	13	1	0.0	0.0	1202.0	0.0	4.0	10180.215000	90000.0	95940.0	90000.000000	11	1	1	-146	53	12.0	365243.0	-116.0	214.0	365243.0	365243.0	0	1	1	1	1	1	1	1	1	1	0	1	1	0	1	1	1	1	0	0	0	1	0	1	0	0	0	0	0	1	1	0	0	0	0	1	1	0	1	0	1	1	0	0	1	1	0	1	0	0	1	0	1	0
1030348	0	90000.0	135000.0	6750.0	135000.0	0.010966	17953	-631	-11317.0	1302	2.0	11	1	0.0	0.0	178.0	0.0	2.0	15837.184952	0.0	0.0	226451.191283	12	1	1	-142	30	12.0	365243.0	-825.0	-358.0	-534.0	-494.0	1	1	1	0	1	1	1	1	0	0	1	0	0	0	1	1	1	1	0	0	0	0	1	1	0	0	1	0	0	0	0	0	1	1	1	1	1	0	1	0	1	0	0	1	0	1	0	1	0	0	0	1	0	0
206555	1	225000.0	906615.0	30091.5	688500.0	0.032561	15346	-5040	-5071.0	1121	3.0	14	0	1.0	1.0	120.0	3.0	1.0	15837.184952	0.0	0.0	226451.191283	13	1	1	-120	-1	12.0	365243.0	-825.0	-358.0	-534.0	-494.0	0	1	1	0	1	0	0	0	1	0	0	0	0	1	1	1	1	0	1	0	1	0	0	1	0	0	0	0	0	1	0	0	1	1	1	1	1	0	1	0	1	0	0	1	0	0	1	0	0	1	0	1	0	0
1257561	0	180000.0	495351.0	28566.0	459000.0	0.018634	19463	-11799	-6945.0	3001	2.0	10	0	2.0	2.0	3485.0	0.0	1.0	15837.184952	0.0	0.0	226451.191283	14	1	1	-7	-1	12.0	365243.0	-825.0	-358.0	-534.0	-494.0	0	1	1	0	1	1	1	0	1	0	0	1	0	1	1	1	1	1	0	0	0	1	0	0	1	0	0	0	1	0	0	0	1	1	1	1	1	0	1	0	1	0	0	1	0	0	1	0	0	1	0	1	0	0
1283370	0	135000.0	835605.0	24561.0	697500.0	0.019689	16011	-951	-5757.0	4664	2.0	11	0	0.0	0.0	1932.0	0.0	0.0	5110.020000	38916.0	26928.0	38916.000000	9	1	1	-259	1000	6.0	365243.0	-228.0	-78.0	-78.0	-76.0	0	0	1	0	1	1	1	0	1	0	0	0	1	0	0	1	1	1	0	1	0	0	0	1	0	1	0	1	0	0	0	1	0	0	0	1	1	1	0	1	0	0	1	0	0	1	0	0	1	0	1	0	0	1

	AMT_INCOME_TOTAL	AMT_CREDIT_x	AMT_ANNUITY_x	AMT_GOODS_PRICE_x	REGION_POPULATION_RELATIVE	DAYS_BIRTH	DAYS_EMPLOYED	DAYS_REGISTRATION	DAYS_ID_PUBLISH	CNT_FAM_MEMBERS	HOUR_APPR_PROCESS_START_x	OBS_30_CNT_SOCIAL_CIRCLE	DEF_30_CNT_SOCIAL_CIRCLE	OBS_60_CNT_SOCIAL_CIRCLE	DAYS_LAST_PHONE_CHANGE	AMT_REQ_CREDIT_BUREAU_WEEK	AMT_REQ_CREDIT_BUREAU_MON	AMT_REQ_CREDIT_BUREAU_YEAR	AMT_ANNUITY_y	AMT_APPLICATION	AMT_CREDIT_y	AMT_GOODS_PRICE_y	HOUR_APPR_PROCESS_START_y	FLAG_LAST_APPL_PER_CONTRACT	NFLAG_LAST_APPL_IN_DAY	DAYS_DECISION	SELLERPLACE_AREA	CNT_PAYMENT	DAYS_FIRST_DRAWING	DAYS_FIRST_DUE	DAYS_LAST_DUE_1ST_VERSION	DAYS_LAST_DUE	DAYS_TERMINATION	FLAG_OWN_CAR_1	FLAG_OWN_REALTY_1	FLAG_EMP_PHONE_1	FLAG_WORK_PHONE_1	FLAG_CONT_MOBILE_1	FLAG_PHONE_1	REGION_RATING_CLIENT_2	REGION_RATING_CLIENT_3	REGION_RATING_CLIENT_W_CITY_2	REGION_RATING_CLIENT_W_CITY_3	FLAG_DOCUMENT_3_1	FLAG_DOCUMENT_6_1	NFLAG_INSURED_ON_APPROVAL_1.0	NAME_CONTRACT_TYPE_x_Revolving loans	CODE_GENDER_M	NAME_TYPE_SUITE_x_Family	NAME_TYPE_SUITE_x_Spouse, partner	NAME_TYPE_SUITE_x_Unaccompanied	NAME_INCOME_TYPE_Pensioner	NAME_INCOME_TYPE_Working	NAME_EDUCATION_TYPE_Higher education	NAME_EDUCATION_TYPE_Secondary / secondary special	NAME_FAMILY_STATUS_Married	NAME_FAMILY_STATUS_Separated	NAME_HOUSING_TYPE_House / apartment	WEEKDAY_APPR_PROCESS_START_x_MONDAY	WEEKDAY_APPR_PROCESS_START_x_THURSDAY	WEEKDAY_APPR_PROCESS_START_x_TUESDAY	ORGANIZATION_TYPE_Business Entity Type 3	ORGANIZATION_TYPE_Construction	ORGANIZATION_TYPE_Self-employed	ORGANIZATION_TYPE_Transport: type 3	ORGANIZATION_TYPE_XNA	NAME_CONTRACT_TYPE_y_Consumer loans	NAME_CONTRACT_TYPE_y_Revolving loans	WEEKDAY_APPR_PROCESS_START_y_SATURDAY	WEEKDAY_APPR_PROCESS_START_y_SUNDAY	WEEKDAY_APPR_PROCESS_START_y_THURSDAY	WEEKDAY_APPR_PROCESS_START_y_TUESDAY	NAME_CASH_LOAN_PURPOSE_XAP	NAME_CASH_LOAN_PURPOSE_XNA	NAME_CONTRACT_STATUS_Canceled	NAME_PAYMENT_TYPE_XNA	CODE_REJECT_REASON_XAP	NAME_TYPE_SUITE_y_Family	NAME_TYPE_SUITE_y_Spouse, partner	NAME_TYPE_SUITE_y_Unaccompanied	NAME_CLIENT_TYPE_Repeater	NAME_GOODS_CATEGORY_Mobile	NAME_GOODS_CATEGORY_XNA	NAME_PORTFOLIO_POS	NAME_PORTFOLIO_XNA	CHANNEL_TYPE_Country-wide	CHANNEL_TYPE_Credit and cash offices	NAME_SELLER_INDUSTRY_Connectivity	NAME_SELLER_INDUSTRY_XNA	NAME_YIELD_GROUP_low_normal	PRODUCT_COMBINATION_Cash	PRODUCT_COMBINATION_POS mobile with interest
886912	225000.0	540000.0	30280.5	540000.0	0.035792	16136	-4914	-8152.0	4305	2.0	19	0.0	0.0	0.0	611.0	1.0	1.0	7.0	15837.184952	0.0	0.0	226451.191283	14	1	1	-254	-1	12.0	365243.0	-825.0	-358.0	-534.0	-494.0	0	0	1	0	1	1	1	0	1	0	1	0	0	0	1	0	0	1	0	1	1	0	1	0	1	1	0	0	1	0	0	0	0	0	0	0	1	0	0	0	1	1	1	1	0	0	1	1	0	1	0	1	0	1	0	1	0	1	0
1345274	225000.0	387000.0	14719.5	387000.0	0.018209	21455	-3406	-12828.0	4196	2.0	15	4.0	0.0	4.0	1067.0	0.0	0.0	3.0	15837.184952	0.0	0.0	226451.191283	9	1	1	-27	-1	12.0	365243.0	-825.0	-358.0	-534.0	-494.0	0	1	1	0	1	1	0	1	0	1	1	0	0	0	1	0	1	0	0	0	0	1	1	0	1	0	0	0	0	0	0	1	0	0	0	1	0	0	0	0	1	1	1	1	0	0	1	1	0	1	0	1	0	1	0	1	0	1	0
710187	202500.0	157500.0	7875.0	157500.0	0.019101	20914	-1229	-1980.0	1985	2.0	17	0.0	0.0	0.0	985.0	0.0	0.0	0.0	15837.184952	0.0	0.0	226451.191283	11	1	1	-19	-1	12.0	365243.0	-825.0	-358.0	-534.0	-494.0	1	1	1	0	1	0	1	0	1	0	0	0	0	1	1	1	0	0	0	1	0	1	1	0	1	0	0	1	0	0	1	0	0	0	1	0	0	1	0	1	0	1	1	1	0	0	1	1	0	1	0	1	0	1	0	1	0	0	0
969891	112500.0	450000.0	24543.0	450000.0	0.028663	20557	365243	-23.0	3445	1.0	14	1.0	1.0	1.0	0.0	0.0	0.0	0.0	9131.760000	70267.5	68454.0	70267.500000	14	1	1	-2678	80	10.0	365243.0	-2647.0	-2377.0	-2377.0	-2370.0	0	1	0	0	1	0	1	0	1	0	0	1	1	0	0	1	0	0	1	0	0	1	0	1	1	0	1	0	0	0	0	0	1	1	0	0	1	0	0	1	0	0	0	1	1	0	0	0	1	0	1	0	1	0	1	0	1	0	1
1169924	225000.0	1408806.0	92457.0	1350000.0	0.031329	18667	-564	-5628.0	2207	2.0	10	0.0	0.0	0.0	2782.0	0.0	0.0	0.0	6621.795000	47533.5	23242.5	47533.500000	12	1	1	-2782	30	4.0	365243.0	-2751.0	-2661.0	-2661.0	-2609.0	1	1	1	1	1	1	1	0	1	0	1	0	1	0	1	0	0	1	0	1	0	1	1	0	1	0	0	0	0	1	0	0	0	1	0	0	0	0	1	1	0	0	0	1	0	1	0	0	1	0	1	0	1	0	1	0	1	0	1

	CNT_CHILDREN	AMT_INCOME_TOTAL	AMT_CREDIT_x	AMT_ANNUITY_x	AMT_GOODS_PRICE_x	REGION_POPULATION_RELATIVE	DAYS_BIRTH	DAYS_EMPLOYED	DAYS_REGISTRATION	DAYS_ID_PUBLISH	CNT_FAM_MEMBERS	HOUR_APPR_PROCESS_START_x	LIVE_CITY_NOT_WORK_CITY	OBS_30_CNT_SOCIAL_CIRCLE	DEF_30_CNT_SOCIAL_CIRCLE	OBS_60_CNT_SOCIAL_CIRCLE	DEF_60_CNT_SOCIAL_CIRCLE	DAYS_LAST_PHONE_CHANGE	AMT_REQ_CREDIT_BUREAU_MON	AMT_REQ_CREDIT_BUREAU_QRT	AMT_REQ_CREDIT_BUREAU_YEAR	AMT_ANNUITY_y	AMT_APPLICATION	AMT_CREDIT_y	AMT_GOODS_PRICE_y	HOUR_APPR_PROCESS_START_y	FLAG_LAST_APPL_PER_CONTRACT	NFLAG_LAST_APPL_IN_DAY	DAYS_DECISION	SELLERPLACE_AREA	CNT_PAYMENT	DAYS_FIRST_DRAWING	DAYS_FIRST_DUE	DAYS_LAST_DUE_1ST_VERSION	DAYS_LAST_DUE	DAYS_TERMINATION	FLAG_OWN_REALTY_1	FLAG_EMP_PHONE_1	FLAG_CONT_MOBILE_1	REGION_RATING_CLIENT_2	REGION_RATING_CLIENT_W_CITY_2	REG_CITY_NOT_WORK_CITY_1	FLAG_DOCUMENT_3_1	FLAG_DOCUMENT_6_1	NFLAG_INSURED_ON_APPROVAL_1.0	CODE_GENDER_M	NAME_TYPE_SUITE_x_Unaccompanied	NAME_INCOME_TYPE_Pensioner	NAME_INCOME_TYPE_State servant	NAME_INCOME_TYPE_Working	NAME_EDUCATION_TYPE_Higher education	NAME_EDUCATION_TYPE_Secondary / secondary special	NAME_FAMILY_STATUS_Married	NAME_HOUSING_TYPE_House / apartment	NAME_HOUSING_TYPE_With parents	WEEKDAY_APPR_PROCESS_START_x_MONDAY	WEEKDAY_APPR_PROCESS_START_x_SUNDAY	WEEKDAY_APPR_PROCESS_START_x_THURSDAY	WEEKDAY_APPR_PROCESS_START_x_TUESDAY	ORGANIZATION_TYPE_Business Entity Type 2	ORGANIZATION_TYPE_Construction	ORGANIZATION_TYPE_School	ORGANIZATION_TYPE_XNA	NAME_CONTRACT_TYPE_y_Consumer loans	WEEKDAY_APPR_PROCESS_START_y_MONDAY	WEEKDAY_APPR_PROCESS_START_y_SUNDAY	WEEKDAY_APPR_PROCESS_START_y_THURSDAY	WEEKDAY_APPR_PROCESS_START_y_TUESDAY	NAME_CASH_LOAN_PURPOSE_XAP	NAME_CASH_LOAN_PURPOSE_XNA	NAME_CONTRACT_STATUS_Canceled	NAME_CONTRACT_STATUS_Unused offer	NAME_PAYMENT_TYPE_XNA	CODE_REJECT_REASON_XAP	NAME_TYPE_SUITE_y_Family	NAME_TYPE_SUITE_y_Unaccompanied	NAME_CLIENT_TYPE_Repeater	NAME_GOODS_CATEGORY_Computers	NAME_GOODS_CATEGORY_Consumer Electronics	NAME_GOODS_CATEGORY_Homewares	NAME_GOODS_CATEGORY_XNA	NAME_PORTFOLIO_Cash	NAME_PORTFOLIO_POS	NAME_PORTFOLIO_XNA	NAME_PRODUCT_TYPE_x-sell	CHANNEL_TYPE_Country-wide	CHANNEL_TYPE_Credit and cash offices	CHANNEL_TYPE_Stone	NAME_SELLER_INDUSTRY_Construction	NAME_SELLER_INDUSTRY_Consumer electronics	NAME_SELLER_INDUSTRY_XNA	NAME_YIELD_GROUP_low_action	NAME_YIELD_GROUP_low_normal	NAME_YIELD_GROUP_middle	PRODUCT_COMBINATION_Cash	PRODUCT_COMBINATION_Cash X-Sell: low	PRODUCT_COMBINATION_POS household with interest	PRODUCT_COMBINATION_POS industry without interest
563940	0	202500.0	1024740.0	52452.0	900000.0	0.007114	19631	365243	-174.0	3177	2.0	13	0	2.0	0.0	2.0	0.0	159.0	0.0	0.0	8.0	15837.184952	0.0	0.0	226451.191283	12	1	1	-169	-1	12.0	365243.0	-825.0	-358.0	-534.0	-494.0	1	0	1	1	1	0	0	1	0	1	1	1	0	0	1	0	1	1	0	0	0	0	1	0	0	0	1	0	1	0	0	0	0	1	1	0	1	1	0	1	1	0	0	0	1	0	0	1	0	0	1	0	0	0	1	0	0	0	1	0	0	0
186208	0	112500.0	468733.5	21982.5	387000.0	0.022800	19606	-336	-3935.0	3085	2.0	9	1	1.0	1.0	1.0	1.0	1815.0	0.0	0.0	1.0	15837.184952	133065.0	133065.0	133065.000000	9	1	1	-1815	1882	12.0	365243.0	-825.0	-358.0	-534.0	-494.0	1	1	1	1	1	1	1	0	0	1	1	0	0	1	0	1	1	1	0	0	0	0	1	1	0	0	0	1	0	1	0	0	1	0	0	1	0	0	1	0	1	1	0	0	0	0	0	1	0	1	0	0	0	1	0	0	0	0	0	0	1	0
739774	0	270000.0	566055.0	18387.0	472500.0	0.018801	21797	-6903	-6437.0	4015	2.0	14	0	0.0	0.0	0.0	0.0	1495.0	0.0	2.0	1.0	13481.955000	174411.0	174411.0	174411.000000	17	1	1	-734	15	14.0	365243.0	-700.0	-310.0	-490.0	-484.0	1	1	1	1	1	0	1	0	0	0	1	0	1	0	1	0	0	1	0	1	0	0	0	0	0	1	0	1	0	0	0	1	1	0	0	0	0	1	0	1	1	0	0	1	0	0	1	0	0	0	0	1	1	0	0	1	0	0	0	0	0	1
767186	0	90000.0	175500.0	15192.0	175500.0	0.014520	21014	365243	-3963.0	3963	2.0	9	0	1.0	0.0	1.0	0.0	601.0	0.0	1.0	4.0	17607.240000	121941.0	95215.5	121941.000000	13	1	1	-601	2500	6.0	365243.0	-570.0	-420.0	-450.0	-441.0	1	0	1	1	1	0	0	1	0	0	1	1	0	0	1	0	1	1	0	0	1	0	0	0	0	0	1	1	1	0	0	0	1	0	0	0	1	1	0	1	0	0	1	0	0	0	1	0	0	1	0	0	0	1	0	0	0	1	0	0	1	0
502320	1	157500.0	492862.5	24102.0	346500.0	0.018801	13246	-1565	-7112.0	4909	3.0	6	1	0.0	0.0	0.0	0.0	0.0	1.0	0.0	3.0	8335.980000	229500.0	265477.5	229500.000000	7	1	1	-252	-1	48.0	365243.0	-222.0	1188.0	365243.0	365243.0	0	1	1	1	1	1	1	0	1	1	1	0	0	1	0	1	1	0	1	0	0	1	0	0	1	0	0	0	0	0	1	0	0	1	0	0	0	1	0	1	1	0	0	0	1	1	0	0	1	0	1	0	0	0	1	0	1	0	0	1	0	0

	CNT_CHILDREN	AMT_INCOME_TOTAL	AMT_CREDIT_x	AMT_ANNUITY_x	AMT_GOODS_PRICE_x	REGION_POPULATION_RELATIVE	DAYS_BIRTH	DAYS_EMPLOYED	DAYS_REGISTRATION	DAYS_ID_PUBLISH	CNT_FAM_MEMBERS	HOUR_APPR_PROCESS_START_x	LIVE_CITY_NOT_WORK_CITY	OBS_30_CNT_SOCIAL_CIRCLE	DEF_30_CNT_SOCIAL_CIRCLE	OBS_60_CNT_SOCIAL_CIRCLE	DEF_60_CNT_SOCIAL_CIRCLE	DAYS_LAST_PHONE_CHANGE	AMT_REQ_CREDIT_BUREAU_HOUR	AMT_REQ_CREDIT_BUREAU_DAY	AMT_REQ_CREDIT_BUREAU_WEEK	AMT_REQ_CREDIT_BUREAU_MON	AMT_REQ_CREDIT_BUREAU_QRT	AMT_REQ_CREDIT_BUREAU_YEAR	AMT_ANNUITY_y	AMT_APPLICATION	AMT_CREDIT_y	AMT_GOODS_PRICE_y	HOUR_APPR_PROCESS_START_y	FLAG_LAST_APPL_PER_CONTRACT	NFLAG_LAST_APPL_IN_DAY	DAYS_DECISION	SELLERPLACE_AREA	CNT_PAYMENT	DAYS_FIRST_DRAWING	DAYS_FIRST_DUE	DAYS_LAST_DUE_1ST_VERSION	DAYS_LAST_DUE	DAYS_TERMINATION	FLAG_OWN_CAR_1	FLAG_OWN_REALTY_1	FLAG_EMP_PHONE_1	FLAG_WORK_PHONE_1	FLAG_CONT_MOBILE_1	FLAG_PHONE_1	REGION_RATING_CLIENT_2	REGION_RATING_CLIENT_3	REGION_RATING_CLIENT_W_CITY_2	REGION_RATING_CLIENT_W_CITY_3	FLAG_DOCUMENT_3_1	FLAG_DOCUMENT_6_1	NFLAG_INSURED_ON_APPROVAL_1.0	NAME_CONTRACT_TYPE_x_Revolving loans	CODE_GENDER_M	NAME_TYPE_SUITE_x_Family	NAME_TYPE_SUITE_x_Spouse, partner	NAME_TYPE_SUITE_x_Unaccompanied	NAME_INCOME_TYPE_Pensioner	NAME_INCOME_TYPE_Working	NAME_EDUCATION_TYPE_Higher education	NAME_EDUCATION_TYPE_Secondary / secondary special	NAME_FAMILY_STATUS_Married	NAME_FAMILY_STATUS_Separated	NAME_HOUSING_TYPE_House / apartment	WEEKDAY_APPR_PROCESS_START_x_MONDAY	WEEKDAY_APPR_PROCESS_START_x_THURSDAY	WEEKDAY_APPR_PROCESS_START_x_TUESDAY	ORGANIZATION_TYPE_Business Entity Type 3	ORGANIZATION_TYPE_Construction	ORGANIZATION_TYPE_Self-employed	ORGANIZATION_TYPE_Transport: type 3	ORGANIZATION_TYPE_XNA	NAME_CONTRACT_TYPE_y_Consumer loans	NAME_CONTRACT_TYPE_y_Revolving loans	WEEKDAY_APPR_PROCESS_START_y_SATURDAY	WEEKDAY_APPR_PROCESS_START_y_SUNDAY	WEEKDAY_APPR_PROCESS_START_y_THURSDAY	WEEKDAY_APPR_PROCESS_START_y_TUESDAY	NAME_CASH_LOAN_PURPOSE_XAP	NAME_CASH_LOAN_PURPOSE_XNA	NAME_CONTRACT_STATUS_Canceled	NAME_PAYMENT_TYPE_XNA	CODE_REJECT_REASON_XAP	NAME_TYPE_SUITE_y_Family	NAME_TYPE_SUITE_y_Spouse, partner	NAME_TYPE_SUITE_y_Unaccompanied	NAME_CLIENT_TYPE_Repeater	NAME_GOODS_CATEGORY_Mobile	NAME_GOODS_CATEGORY_XNA	NAME_PORTFOLIO_POS	NAME_PORTFOLIO_XNA	CHANNEL_TYPE_Country-wide	CHANNEL_TYPE_Credit and cash offices	NAME_SELLER_INDUSTRY_Connectivity	NAME_SELLER_INDUSTRY_XNA	NAME_YIELD_GROUP_low_normal	PRODUCT_COMBINATION_Cash	PRODUCT_COMBINATION_POS mobile with interest
886912	-0.565295	0.602840	-0.109029	0.237550	0.049634	1.195677	-0.040396	-0.515113	-0.903322	0.827966	-0.164389	2.189600	-0.46203	-0.622475	-0.333640	-0.621366	-0.283858	-0.580375	-0.072306	-0.064286	5.608317	0.774544	-0.45678	1.873421	0.006095	-0.598698	-0.616825	0.008398	0.465356	0.068673	0.059004	0.803143	-0.206051	-0.232557	0.206821	-0.161489	-0.250496	-0.385506	-0.402045	0	0	1	0	1	1	1	0	1	0	1	0	0	0	1	0	0	1	0	1	1	0	1	0	1	1	0	0	1	0	0	0	0	0	0	0	1	0	0	0	1	1	1	1	0	0	1	1	0	1	0	1	0	1	0	1	0	1	0
1345274	-0.565295	0.602840	-0.504282	-0.882596	-0.382168	-0.168180	1.182491	-0.504841	-2.227636	0.755375	-0.164389	0.948029	-0.46203	1.002743	-0.333640	1.016886	-0.283858	-0.010246	-0.072306	-0.064286	-0.168591	-0.284108	-0.45678	0.160139	0.006095	-0.598698	-0.616825	0.008398	-1.047544	0.068673	0.059004	1.089453	-0.206051	-0.232557	0.206821	-0.161489	-0.250496	-0.385506	-0.402045	0	1	1	0	1	1	0	1	0	1	1	0	0	0	1	0	1	0	0	0	0	1	1	0	1	0	0	0	0	0	0	1	0	0	0	1	0	0	0	0	1	1	1	1	0	0	1	1	0	1	0	1	0	1	0	1	0	1	0
710187	-0.565295	0.347182	-1.097161	-1.375291	-1.029872	-0.098990	1.058110	-0.490013	0.844681	-0.717089	-0.164389	1.568814	-0.46203	-0.622475	-0.333640	-0.621366	-0.283858	-0.112770	-0.072306	-0.064286	-0.168591	-0.284108	-0.45678	-1.124822	0.006095	-0.598698	-0.616825	0.008398	-0.442384	0.068673	0.059004	1.099543	-0.206051	-0.232557	0.206821	-0.161489	-0.250496	-0.385506	-0.402045	1	1	1	0	1	0	1	0	1	0	0	0	0	1	1	1	0	0	0	1	0	1	1	0	1	0	0	1	0	0	1	0	0	0	1	0	0	1	0	1	0	1	1	1	0	0	1	1	0	1	0	1	0	1	0	1	0	0	0
969891	-0.565295	-0.675449	-0.341531	-0.175459	-0.204367	0.642704	0.976033	2.006208	1.398933	0.255230	-1.292547	0.637636	-0.46203	-0.216171	1.789523	-0.211803	-0.283858	-1.344297	-0.072306	-0.064286	-0.168591	-0.284108	-0.45678	-1.124822	-0.516710	-0.355134	-0.398309	-0.563952	0.465356	0.068673	0.059004	-2.254190	-0.147522	-0.388368	0.206821	-0.192560	-0.273737	-0.400448	-0.416799	0	1	0	0	1	0	1	0	1	0	0	1	1	0	0	1	0	0	1	0	0	1	0	1	1	0	1	0	0	0	0	0	1	1	0	0	1	0	0	1	0	0	0	1	1	0	0	0	1	0	1	0	1	0	1	0	1	0	1
1169924	-0.565295	0.602840	2.135401	4.713275	2.335648	0.849497	0.541504	-0.485483	-0.188488	-0.569243	-0.164389	-0.603936	-0.46203	-0.622475	-0.333640	-0.621366	-0.283858	2.133986	-0.072306	-0.064286	-0.168591	-0.284108	-0.45678	-1.124822	-0.712406	-0.433935	-0.542631	-0.647263	-0.139804	0.068673	0.059004	-2.385363	-0.183651	-0.855803	0.206821	-0.194333	-0.277006	-0.402750	-0.418678	1	1	1	1	1	1	1	0	1	0	1	0	1	0	1	0	0	1	0	1	0	1	1	0	1	0	0	0	0	1	0	0	0	1	0	0	0	0	1	1	0	0	0	1	0	1	0	0	1	0	1	0	1	0	1	0	1	0	1

	CNT_CHILDREN	AMT_INCOME_TOTAL	AMT_CREDIT_x	AMT_ANNUITY_x	AMT_GOODS_PRICE_x	REGION_POPULATION_RELATIVE	DAYS_BIRTH	DAYS_EMPLOYED	DAYS_REGISTRATION	DAYS_ID_PUBLISH	CNT_FAM_MEMBERS	HOUR_APPR_PROCESS_START_x	LIVE_CITY_NOT_WORK_CITY	OBS_30_CNT_SOCIAL_CIRCLE	DEF_30_CNT_SOCIAL_CIRCLE	OBS_60_CNT_SOCIAL_CIRCLE	DEF_60_CNT_SOCIAL_CIRCLE	DAYS_LAST_PHONE_CHANGE	AMT_REQ_CREDIT_BUREAU_HOUR	AMT_REQ_CREDIT_BUREAU_DAY	AMT_REQ_CREDIT_BUREAU_WEEK	AMT_REQ_CREDIT_BUREAU_MON	AMT_REQ_CREDIT_BUREAU_QRT	AMT_REQ_CREDIT_BUREAU_YEAR	AMT_ANNUITY_y	AMT_APPLICATION	AMT_CREDIT_y	AMT_GOODS_PRICE_y	HOUR_APPR_PROCESS_START_y	FLAG_LAST_APPL_PER_CONTRACT	NFLAG_LAST_APPL_IN_DAY	DAYS_DECISION	SELLERPLACE_AREA	CNT_PAYMENT	DAYS_FIRST_DRAWING	DAYS_FIRST_DUE	DAYS_LAST_DUE_1ST_VERSION	DAYS_LAST_DUE	DAYS_TERMINATION	FLAG_OWN_REALTY_1	FLAG_EMP_PHONE_1	FLAG_CONT_MOBILE_1	REGION_RATING_CLIENT_2	REGION_RATING_CLIENT_W_CITY_2	REG_CITY_NOT_WORK_CITY_1	FLAG_DOCUMENT_3_1	FLAG_DOCUMENT_6_1	NFLAG_INSURED_ON_APPROVAL_1.0	CODE_GENDER_M	NAME_TYPE_SUITE_x_Unaccompanied	NAME_INCOME_TYPE_Pensioner	NAME_INCOME_TYPE_State servant	NAME_INCOME_TYPE_Working	NAME_EDUCATION_TYPE_Higher education	NAME_EDUCATION_TYPE_Secondary / secondary special	NAME_FAMILY_STATUS_Married	NAME_HOUSING_TYPE_House / apartment	NAME_HOUSING_TYPE_With parents	WEEKDAY_APPR_PROCESS_START_x_MONDAY	WEEKDAY_APPR_PROCESS_START_x_SUNDAY	WEEKDAY_APPR_PROCESS_START_x_THURSDAY	WEEKDAY_APPR_PROCESS_START_x_TUESDAY	ORGANIZATION_TYPE_Business Entity Type 2	ORGANIZATION_TYPE_Construction	ORGANIZATION_TYPE_School	ORGANIZATION_TYPE_XNA	NAME_CONTRACT_TYPE_y_Consumer loans	WEEKDAY_APPR_PROCESS_START_y_MONDAY	WEEKDAY_APPR_PROCESS_START_y_SUNDAY	WEEKDAY_APPR_PROCESS_START_y_THURSDAY	WEEKDAY_APPR_PROCESS_START_y_TUESDAY	NAME_CASH_LOAN_PURPOSE_XAP	NAME_CASH_LOAN_PURPOSE_XNA	NAME_CONTRACT_STATUS_Canceled	NAME_CONTRACT_STATUS_Unused offer	NAME_PAYMENT_TYPE_XNA	CODE_REJECT_REASON_XAP	NAME_TYPE_SUITE_y_Family	NAME_TYPE_SUITE_y_Unaccompanied	NAME_CLIENT_TYPE_Repeater	NAME_GOODS_CATEGORY_Computers	NAME_GOODS_CATEGORY_Consumer Electronics	NAME_GOODS_CATEGORY_Homewares	NAME_GOODS_CATEGORY_XNA	NAME_PORTFOLIO_Cash	NAME_PORTFOLIO_POS	NAME_PORTFOLIO_XNA	NAME_PRODUCT_TYPE_x-sell	CHANNEL_TYPE_Country-wide	CHANNEL_TYPE_Credit and cash offices	CHANNEL_TYPE_Stone	NAME_SELLER_INDUSTRY_Construction	NAME_SELLER_INDUSTRY_Consumer electronics	NAME_SELLER_INDUSTRY_XNA	NAME_YIELD_GROUP_low_action	NAME_YIELD_GROUP_low_normal	NAME_YIELD_GROUP_middle	PRODUCT_COMBINATION_Cash	PRODUCT_COMBINATION_Cash X-Sell: low	PRODUCT_COMBINATION_POS household with interest	PRODUCT_COMBINATION_POS industry without interest
563940	-1.363375	-1.953734	-1.504036	-1.942035	-1.474372	-81.379969	-3.750036	-0.481628	1.405831	-2.038992	-2.606161	-3.606291	-1.675502	-0.545223	-1.042012	-0.540370	-1.012305	-1.345729	-0.955689	-0.984741	-1.142528	-0.584879	-1.107973	-0.138939	-1.228691	-0.598700	-0.616827	-0.821454	-3.813066	-13.556997	-15.944536	1.124656	-0.205477	-1.185544	-4.821163	-0.147423	-0.246378	-0.381180	-0.398163	1	0	1	1	1	0	0	1	0	1	1	1	0	0	1	0	1	1	0	0	0	0	1	0	0	0	1	0	1	0	0	0	0	1	1	0	1	1	0	1	1	0	0	0	1	0	0	1	0	0	1	0	0	0	1	0	0	0	1	0	0	0
186208	-1.363375	-1.953745	-1.504039	-1.942193	-1.474376	12.996496	-3.750038	-0.481645	1.405530	-2.039033	-2.606161	-3.991666	5.222424	-0.710306	3.465808	-0.708112	5.573290	-1.343140	-0.955689	-0.984741	-1.142528	-0.584879	-1.107973	-1.423148	-1.228691	-0.598698	-0.616825	-0.821455	-4.087730	-13.556997	-15.944536	1.122037	-0.204494	-1.185544	-4.821163	-0.147423	-0.246378	-0.381180	-0.398163	1	1	1	1	1	1	1	0	0	1	1	0	0	1	0	1	1	1	0	0	0	0	1	1	0	0	0	1	0	1	0	0	1	0	0	1	0	0	1	0	1	1	0	0	0	0	0	1	0	1	0	0	0	1	0	0	0	0	0	0	1	0
739774	-1.363375	-1.953725	-1.504039	-1.942211	-1.474376	-11.063907	-3.749922	-0.481645	1.405329	-2.038621	-2.606161	-3.509947	-1.675502	-0.875390	-1.042012	-0.875854	-1.012305	-1.343640	-0.955689	-0.984741	-1.142528	-0.584879	2.956800	-1.423148	-1.228705	-0.598698	-0.616825	-0.821455	-3.355293	-13.556997	-15.944536	1.123757	-0.205469	-1.173405	-4.821163	-0.147423	-0.246378	-0.381180	-0.398163	1	1	1	1	1	0	1	0	0	0	1	0	1	0	1	0	0	1	0	1	0	0	0	0	0	1	0	1	0	0	0	1	1	0	0	0	0	1	0	1	1	0	0	1	0	0	1	0	0	0	0	1	1	0	0	1	0	0	0	0	0	1
767186	-1.363375	-1.953748	-1.504041	-1.942228	-1.474378	-36.820993	-3.749963	-0.481628	1.405527	-2.038644	-2.606161	-3.991666	-1.675502	-0.710306	-1.042012	-0.708112	-1.012305	-1.345038	-0.955689	-0.984741	-1.142528	-0.584879	0.924413	-0.872773	-1.228680	-0.598699	-0.616826	-0.821455	-3.721512	-13.556997	-15.944536	1.123968	-0.204171	-1.221960	-4.821163	-0.147423	-0.246378	-0.381180	-0.398163	1	0	1	1	1	0	0	1	0	0	1	1	0	0	1	0	1	1	0	0	1	0	0	0	0	0	1	1	1	0	0	0	1	0	0	0	1	1	0	1	0	0	1	0	0	0	1	0	0	1	0	0	0	1	0	0	0	1	0	0	1	0
502320	0.629792	-1.953739	-1.504039	-1.942182	-1.474377	-11.063907	-3.750374	-0.481645	1.405275	-2.038224	-1.333421	-4.280697	5.222424	-0.875390	-1.042012	-0.875854	-1.012305	-1.345977	-0.955689	-0.984741	-1.142528	0.535865	-1.107973	-1.056231	-1.228736	-0.598697	-0.616824	-0.821454	-4.270840	-13.556997	-15.944536	1.124524	-0.205477	-0.967049	-4.821163	-0.147423	-0.246378	-0.381156	-0.398141	0	1	1	1	1	1	1	0	1	1	1	0	0	1	0	1	1	0	1	0	0	1	0	0	1	0	0	0	0	0	1	0	0	1	0	0	0	1	0	1	1	0	0	0	1	1	0	0	1	0	1	0	0	0	1	0	1	0	0	1	0	0

	application_data	SK_ID_CURR	ID of loan in our sample	Unnamed: 4
0	application_data	TARGET	Target variable (1 - client with payment difficulties: he/she had late payment more than X days on at least one of the first Y installments of the loan in our sample, 0 - all other cases)	NaN
1	application_data	NAME_CONTRACT_TYPE	Identification if loan is cash or revolving	NaN
2	application_data	CODE_GENDER	Gender of the client	NaN
3	application_data	FLAG_OWN_CAR	Flag if the client owns a car	NaN
4	application_data	FLAG_OWN_REALTY	Flag if client owns a house or flat	NaN
5	application_data	CNT_CHILDREN	Number of children the client has	NaN
6	application_data	AMT_INCOME_TOTAL	Income of the client	NaN
7	application_data	AMT_CREDIT	Credit amount of the loan	NaN
8	application_data	AMT_ANNUITY	Loan annuity	NaN
9	application_data	AMT_GOODS_PRICE	For consumer loans it is the price of the goods for which the loan is given	NaN
10	application_data	NAME_TYPE_SUITE	Who was accompanying client when he was applying for the loan	NaN
11	application_data	NAME_INCOME_TYPE	Clients income type (businessman, working, maternity leave,…)	NaN
12	application_data	NAME_EDUCATION_TYPE	Level of highest education the client achieved	NaN
13	application_data	NAME_FAMILY_STATUS	Family status of the client	NaN
14	application_data	NAME_HOUSING_TYPE	What is the housing situation of the client (renting, living with parents, ...)	NaN
15	application_data	REGION_POPULATION_RELATIVE	Normalized population of region where client lives (higher number means the client lives in more populated region)	normalized
16	application_data	DAYS_BIRTH	Client's age in days at the time of application	time only relative to the application
17	application_data	DAYS_EMPLOYED	How many days before the application the person started current employment	time only relative to the application
18	application_data	DAYS_REGISTRATION	How many days before the application did client change his registration	time only relative to the application
19	application_data	DAYS_ID_PUBLISH	How many days before the application did client change the identity document with which he applied for the loan	time only relative to the application
20	application_data	OWN_CAR_AGE	Age of client's car	NaN
21	application_data	FLAG_MOBIL	Did client provide mobile phone (1=YES, 0=NO)	NaN
22	application_data	FLAG_EMP_PHONE	Did client provide work phone (1=YES, 0=NO)	NaN
23	application_data	FLAG_WORK_PHONE	Did client provide home phone (1=YES, 0=NO)	NaN
24	application_data	FLAG_CONT_MOBILE	Was mobile phone reachable (1=YES, 0=NO)	NaN
25	application_data	FLAG_PHONE	Did client provide home phone (1=YES, 0=NO)	NaN
26	application_data	FLAG_EMAIL	Did client provide email (1=YES, 0=NO)	NaN
27	application_data	OCCUPATION_TYPE	What kind of occupation does the client have	NaN
28	application_data	CNT_FAM_MEMBERS	How many family members does client have	NaN
29	application_data	REGION_RATING_CLIENT	Our rating of the region where client lives (1,2,3)	NaN
30	application_data	REGION_RATING_CLIENT_W_CITY	Our rating of the region where client lives with taking city into account (1,2,3)	NaN
31	application_data	WEEKDAY_APPR_PROCESS_START	On which day of the week did the client apply for the loan	NaN
32	application_data	HOUR_APPR_PROCESS_START	Approximately at what hour did the client apply for the loan	rounded
33	application_data	REG_REGION_NOT_LIVE_REGION	Flag if client's permanent address does not match contact address (1=different, 0=same, at region level)	NaN
34	application_data	REG_REGION_NOT_WORK_REGION	Flag if client's permanent address does not match work address (1=different, 0=same, at region level)	NaN
35	application_data	LIVE_REGION_NOT_WORK_REGION	Flag if client's contact address does not match work address (1=different, 0=same, at region level)	NaN
36	application_data	REG_CITY_NOT_LIVE_CITY	Flag if client's permanent address does not match contact address (1=different, 0=same, at city level)	NaN
37	application_data	REG_CITY_NOT_WORK_CITY	Flag if client's permanent address does not match work address (1=different, 0=same, at city level)	NaN
38	application_data	LIVE_CITY_NOT_WORK_CITY	Flag if client's contact address does not match work address (1=different, 0=same, at city level)	NaN
39	application_data	ORGANIZATION_TYPE	Type of organization where client works	NaN

	FLAG_OWN_CAR_1	FLAG_OWN_REALTY_1	FLAG_EMP_PHONE_1	FLAG_WORK_PHONE_1	FLAG_CONT_MOBILE_1	FLAG_PHONE_1	REGION_RATING_CLIENT_2	REGION_RATING_CLIENT_W_CITY_2	FLAG_DOCUMENT_3_1	NFLAG_INSURED_ON_APPROVAL_1.0	NAME_CONTRACT_TYPE_x_Revolving loans	CODE_GENDER_M	NAME_TYPE_SUITE_x_Family	NAME_TYPE_SUITE_x_Unaccompanied	NAME_INCOME_TYPE_State servant	NAME_INCOME_TYPE_Working	NAME_EDUCATION_TYPE_Higher education	NAME_EDUCATION_TYPE_Secondary / secondary special	NAME_FAMILY_STATUS_Married	NAME_FAMILY_STATUS_Single / not married	NAME_HOUSING_TYPE_House / apartment	WEEKDAY_APPR_PROCESS_START_x_MONDAY	WEEKDAY_APPR_PROCESS_START_x_WEDNESDAY	ORGANIZATION_TYPE_Business Entity Type 3	ORGANIZATION_TYPE_Government	ORGANIZATION_TYPE_School	NAME_CONTRACT_TYPE_y_Consumer loans	WEEKDAY_APPR_PROCESS_START_y_SATURDAY	WEEKDAY_APPR_PROCESS_START_y_SUNDAY	NAME_CASH_LOAN_PURPOSE_XAP	NAME_CASH_LOAN_PURPOSE_XNA	NAME_PAYMENT_TYPE_XNA	CODE_REJECT_REASON_XAP	NAME_TYPE_SUITE_y_Family	NAME_TYPE_SUITE_y_Unaccompanied	NAME_CLIENT_TYPE_Refreshed	NAME_CLIENT_TYPE_Repeater	NAME_GOODS_CATEGORY_Consumer Electronics	NAME_GOODS_CATEGORY_Furniture	NAME_GOODS_CATEGORY_Mobile	NAME_GOODS_CATEGORY_Vehicles	NAME_GOODS_CATEGORY_XNA	NAME_PORTFOLIO_Cash	NAME_PORTFOLIO_POS	NAME_PRODUCT_TYPE_x-sell	CHANNEL_TYPE_Country-wide	CHANNEL_TYPE_Credit and cash offices	CHANNEL_TYPE_Regional / Local	CHANNEL_TYPE_Stone	NAME_SELLER_INDUSTRY_Connectivity	NAME_SELLER_INDUSTRY_Consumer electronics	NAME_SELLER_INDUSTRY_Furniture	NAME_SELLER_INDUSTRY_XNA	NAME_YIELD_GROUP_low_normal	NAME_YIELD_GROUP_middle	PRODUCT_COMBINATION_Cash X-Sell: low	PRODUCT_COMBINATION_POS household with interest	PRODUCT_COMBINATION_POS industry with interest	PRODUCT_COMBINATION_POS mobile without interest	PRODUCT_COMBINATION_POS other with interest
0	0	1	1	0	1	1	1	1	1	0	0	1	0	1	0	1	0	1	0	1	1	0	1	1	0	0	1	1	0	1	0	1	1	0	1	0	0	0	0	0	1	0	0	1	0	0	0	0	1	0	0	0	0	1	0	0	0	0	0	1
1	0	0	1	0	1	1	0	0	1	1	0	0	1	0	1	0	1	0	1	0	1	1	0	0	0	1	0	0	0	0	1	1	1	0	1	0	1	0	0	0	0	1	1	0	1	0	1	0	0	0	0	0	1	1	0	1	0	0	0	0
2	0	0	1	0	1	1	0	0	1	0	0	0	1	0	1	0	1	0	1	0	1	1	0	0	0	1	1	0	1	1	0	0	1	1	0	1	0	0	1	0	0	0	0	1	0	0	0	0	1	0	0	1	0	0	1	0	0	1	0	0
3	0	0	1	0	1	1	0	0	1	1	0	0	1	0	1	0	1	0	1	0	1	1	0	0	0	1	1	1	0	1	0	0	1	1	0	1	0	1	0	0	0	0	0	1	0	1	0	0	0	0	1	0	0	0	1	0	1	0	0	0
4	1	1	1	1	1	1	1	1	0	0	1	1	0	1	0	1	0	1	0	1	1	1	0	0	1	0	1	0	0	1	0	0	1	0	1	0	0	0	0	1	0	0	0	1	0	0	0	1	0	1	0	0	0	0	1	0	0	0	1	0

	FLAG_OWN_CAR_1	FLAG_OWN_REALTY_1	FLAG_EMP_PHONE_1	FLAG_WORK_PHONE_1	FLAG_CONT_MOBILE_1	FLAG_PHONE_1	REGION_RATING_CLIENT_2	REGION_RATING_CLIENT_W_CITY_2	FLAG_DOCUMENT_3_1	NFLAG_INSURED_ON_APPROVAL_1.0	NAME_CONTRACT_TYPE_x_Revolving loans	CODE_GENDER_M	NAME_TYPE_SUITE_x_Family	NAME_TYPE_SUITE_x_Unaccompanied	NAME_INCOME_TYPE_State servant	NAME_INCOME_TYPE_Working	NAME_EDUCATION_TYPE_Higher education	NAME_EDUCATION_TYPE_Secondary / secondary special	NAME_FAMILY_STATUS_Married	NAME_FAMILY_STATUS_Single / not married	NAME_HOUSING_TYPE_House / apartment	WEEKDAY_APPR_PROCESS_START_x_MONDAY	WEEKDAY_APPR_PROCESS_START_x_WEDNESDAY	ORGANIZATION_TYPE_Business Entity Type 3	ORGANIZATION_TYPE_Government	ORGANIZATION_TYPE_School	NAME_CONTRACT_TYPE_y_Consumer loans	WEEKDAY_APPR_PROCESS_START_y_SATURDAY	WEEKDAY_APPR_PROCESS_START_y_SUNDAY	NAME_CASH_LOAN_PURPOSE_XAP	NAME_CASH_LOAN_PURPOSE_XNA	NAME_PAYMENT_TYPE_XNA	CODE_REJECT_REASON_XAP	NAME_TYPE_SUITE_y_Family	NAME_TYPE_SUITE_y_Unaccompanied	NAME_CLIENT_TYPE_Refreshed	NAME_CLIENT_TYPE_Repeater	NAME_GOODS_CATEGORY_Consumer Electronics	NAME_GOODS_CATEGORY_Furniture	NAME_GOODS_CATEGORY_Mobile	NAME_GOODS_CATEGORY_Vehicles	NAME_GOODS_CATEGORY_XNA	NAME_PORTFOLIO_Cash	NAME_PORTFOLIO_POS	NAME_PRODUCT_TYPE_x-sell	CHANNEL_TYPE_Country-wide	CHANNEL_TYPE_Credit and cash offices	CHANNEL_TYPE_Regional / Local	CHANNEL_TYPE_Stone	NAME_SELLER_INDUSTRY_Connectivity	NAME_SELLER_INDUSTRY_Consumer electronics	NAME_SELLER_INDUSTRY_Furniture	NAME_SELLER_INDUSTRY_XNA	NAME_YIELD_GROUP_low_normal	NAME_YIELD_GROUP_middle	PRODUCT_COMBINATION_Cash X-Sell: low	PRODUCT_COMBINATION_POS household with interest	PRODUCT_COMBINATION_POS industry with interest	PRODUCT_COMBINATION_POS mobile without interest	PRODUCT_COMBINATION_POS other with interest
0	0	1	1	0	1	1	1	1	1	0	0	1	0	1	0	1	0	1	0	1	1	0	1	1	0	0	1	1	0	1	0	1	1	0	1	0	0	0	0	0	1	0	0	1	0	0	0	0	1	0	0	0	0	1	0	0	0	0	0	1
1	0	0	1	0	1	1	0	0	1	1	0	0	1	0	1	0	1	0	1	0	1	1	0	0	0	1	0	0	0	0	1	1	1	0	1	0	1	0	0	0	0	1	1	0	1	0	1	0	0	0	0	0	1	1	0	1	0	0	0	0
2	0	0	1	0	1	1	0	0	1	0	0	0	1	0	1	0	1	0	1	0	1	1	0	0	0	1	1	0	1	1	0	0	1	1	0	1	0	0	1	0	0	0	0	1	0	0	0	0	1	0	0	1	0	0	1	0	0	1	0	0
3	0	0	1	0	1	1	0	0	1	1	0	0	1	0	1	0	1	0	1	0	1	1	0	0	0	1	1	1	0	1	0	0	1	1	0	1	0	1	0	0	0	0	0	1	0	1	0	0	0	0	1	0	0	0	1	0	1	0	0	0
4	1	1	1	1	1	1	1	1	0	0	1	1	0	1	0	1	0	1	0	1	1	1	0	0	1	0	1	0	0	1	0	0	1	0	1	0	0	0	0	1	0	0	0	1	0	0	0	1	0	1	0	0	0	0	1	0	0	0	1	0